ICML 2022 Accepted Papers 1235

If you are an author on a paper listed here and your name or institution is missing, you should immediately update your submission CMT and the corresponding profile at https://ICML.cc/EditProfile. Use your browser's search (ctrl+f or cmd+f) to find your papers.

As you are preparing your camera-ready versions, talks, and posters, please review our guide to make your papers, talks, and posters accessible and inclusive.

Global Optimization Networks
Sen Zhao (Google Research) · Erez Louidor (Google) · Maya Gupta (Univ. Washington)

Spatial-channel Token Distillation of MLP-like Vision Models
Yanxi Li (University of Sydney) · Xinghao Chen (Huawei Noah's Ark Lab) · Minjing Dong (The University of Sydney) · Yehui Tang (Peking University) · Yunhe Wang (Noah's Ark Lab, Huawei Technologies.) · Chang Xu (University of Sydney)

Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
Ling Yang (Peking University) · Shenda Hong (Peking University)

State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural Networks
Yanqi Chen (Peking University) · Zhaofei Yu (Peking University) · Wei Fang (Peking University) · Zhengyu Ma (Peng Cheng Lab) · Tiejun Huang (Peking University) · Yonghong Tian (Peking University)

Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data
Zhengfeng Lai (University of California Davis) · Chao Wang (Southern University of Science and Technology) · Henrry Gunawan (UC Davis) · Senching Cheung (University of Kentucky) · Chen-Nee Chuah (University of California Davis)

QSFL: A Two-Level Uplink Communication Optimization Framework for Federated Learning
Liping Yi (Nankai University) · Wang Gang (Nankai Univerisity) · Liu Xiaoguang (Nankai Univerisity)

MonePipe: Accelerating Momentum Network Training with Pipelines
Hwijoon Lim (KAIST) · Yechan Kim (KAIST) · Jinwoo Shin (KAIST) · Dongsu Han (KAIST)

Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization
Jaehong Yoon (KAIST) · Geon Park (KAIST) · Wonyong Jeong (Korea Advanced Institute of Science and Technology) · Sung Ju Hwang (KAIST, AITRICS)

On Collective Robustness of Bagging Against Data Poisoning
Ruoxin Chen (Shanghai Jiao Tong University) · Zenan Li (Shanghai Jiao Tong University) · Jie Li (Shanghai Jiao Tong University) · Junchi Yan (Shanghai Jiao Tong University) · Chentao Wu (Shanghai Jiao Tong University)

PAC-Net: A Model Pruning Approach to Inductive Transfer Learning
Sanghoon Myung (Samsung Electronics) · In Huh (Samsung Electronics) · Wonik Jang (Samsung Electronics) · Jae Myung Choe (Samsung Electronics) · jisu ryu (Samsung Electronics) · Changwook Jeong (UNIST) · Daesin Kim (Data & Information Technology Center, Samsung Electronics) · Kee-Eung Kim (KAIST)

Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more
Elad Tolochinksy (University of Haifa) · Ibrahim Jubran (The University of Haifa) · Dan Feldman (The University of Haifa)

ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
Jun Xia (Westlake University) · Lirong Wu (Westlake University) · Wang Ge (Westlake University) · Jintao Chen (Zhejiang University) · Stan Z. Li (Westlake University)

Thresholded Lasso Bandit
Kaito Ariu (CyberAgent, Inc. / KTH) · Kenshi Abe (CyberAgent, Inc.) · Alexandre Proutiere (KTH Royal Institute of Technology)

Evolving Curricula with Regret-Based Environment Design
Jack Parker-Holder (University of Oxford) · Minqi Jiang (UCL & FAIR) · Michael Dennis (UC Berkeley) · Mikayel Samvelyan (University College London) · Jakob Foerster (Oxford university) · Edward Grefenstette (Facebook AI Research & UCL) · Tim Rocktäschel (Facebook AI Research & University College London)

DynaMixer: A Vision MLP Architecture with Dynamic Mixing
Ziyu Wang (Tencent) · Wenhao Jiang (Tencent) · Yiming Zhu (Graduate school at ShenZhen,Tsinghua university) · Li Yuan (Peking University) · Yibing Song (Tencent AI Lab) · Wei Liu (Tencent)

AutoSNN: Towards Energy-Efficient Spiking Neural Networks
Byunggook Na (Samsung Advanced Institute of Technology) · Jisoo Mok (Seoul National University) · Seongsik Park (Seoul National University) · Dongjin Lee (Seoul National University) · Hyeokjun Choe (Seoul National University) · Sungroh Yoon (Seoul National University)

Rethinking Fano’s Inequality in Ensemble Learning
Terufumi Morishita (Hitachi, Ltd.) · Gaku Morio (Hitachi, ltd.) · Shota Horiguchi (Hitachi, Ltd.) · Hiroaki Ozaki (Hitachi, Ltd.) · Nobuo Nukaga (Hitachi, Ltd.)

Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
Shiran Zada (Weizmann Institute of Science) · Itay Benou (Weizmann Institute of science) · Michal Irani (Weizmann Institute, Israel)

Prototype-anchored Learning for Learning with Imperfect Annotations
Xiong Zhou (Harbin Institute of Technology) · Xianming Liu (Harbin Institute of Technology) · Deming Zhai (Harbin Institute of Technolgy) · Junjun Jiang (Harbin Institute of Technology) · Xin Gao (Kaust) · Xiangyang Ji (Tsinghua University)

The dynamics of representation learning in shallow, non-linear autoencoders
Maria Refinetti (Laboratoire de Physique de l’Ecole Normale Supérieure Paris) · Sebastian Goldt (International School of Advanced Studies (SISSA))

Exploring the Gap between Collapsed & Whitened Features in Self-Supervised Learning
Bobby He (University of Oxford) · Mete Ozay (Samsung Research UK)

A Joint Exponential Mechanism For Differentially Private Top-$k$
Jennifer Gillenwater (Google Research NYC) · Matthew Joseph (Google) · andres munoz (Google) · Monica Ribero Diaz (University of Texas at Austin / Google)

Policy Gradient Method For Robust Reinforcement Learning
Yue Wang (University at Buffalo) · Shaofeng Zou (University at Buffalo, the State University of New York)

EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning
Shuang Ao (University of Technology Sydney) · Tianyi Zhou (University of Washington) · Jing Jiang (University of Technology Sydney) · Guodong Long (University of Technology Sydney) · Xuan Song () · Chengqi Zhang (University of Technology Sydney)

Regret Minimization with Performative Feedback
Meena Jagadeesan (UC Berkeley) · Tijana Zrnic (University of California, Berkeley) · Celestine Mendler-Dünner (Max Planck Institute for Intelligent Systems)

Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers
Liam Hodgkinson (University of California Berkeley) · Umut Simsekli (Inria/ENS) · Rajiv Khanna (UC Berkeley) · Michael Mahoney (UC Berkeley)

Local Augmentation for Graph Neural Networks
Songtao Liu (The Pennsylvania State University) · Rex (Zhitao) Ying (Stanford University) · Hanze Dong (HKUST) · Lanqing Li (Tencent AI Lab) · Tingyang Xu (Tencent Holdings) · Yu Rong (Tencent AI Lab) · Peilin Zhao (Tencent AI Lab) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab) · Dinghao Wu (Pennsylvania State University)

Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning
Konstantinos Kalais (Cyprus University of Technology) · Sotirios Chatzis (Cyprus University of Technology)

Object Permanence Emerges in a Random Walk along Memory
Pavel Tokmakov (Toyota Research Institute) · Allan Jabri (UC Berkeley) · Jie Li (Toyota Research Institute) · Adrien Gaidon (Toyota Research Institute)

G-Mixup: Graph Data Augmentation for Graph Classification
Xiaotian Han (Texas A&M University) · Zhimeng Jiang (Texas A&M University) · Ninghao Liu (University of Georgia) · Xia Hu (Rice University)

Fourier Learning with Cyclical Data
Yingxiang Yang (UIUC) · Zhihan Xiong (University of Washington) · Tianyi Liu (ByteDance Inc.) · Taiqing Wang (ByteDance) · Chong Wang (ByteDance)

Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
Jongmin Lee (Seoul National university) · Joo Young Choi (Seoul National University) · Ernest Ryu (Seoul National University) · Albert No (Hongik University)

Bayesian Nonparametric Learning for Point Processes with Spatial Homogeneity: A Spatial Analysis of NBA Shot Locations
Fan Yin (Microsoft) · Jieying Jiao (University of Connecticut ) · Guanyu Hu (University of Missouri) · Jun Yan (University of Connecticut)

Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation
Wenxiao Wang (University of Maryland) · Alexander Levine (University of Maryland) · Soheil Feizi (University of Maryland)

Flow-Guided Sparse Transformer for Video Deblurring
Jing Lin (Tsinghua Univisity, Tsinghua Shenzhen International Graduate School) · Yuanhao Cai (Tsinghua Univisity, Tsinghua Shenzhen International Graduate School) · Xiaowan Hu (Tsinghua Univisity, Tsinghua Shenzhen International Graduate School) · Haoqian Wang (Tsinghua Shenzhen International Graduate School, Tsinghua University) · Youliang Yan (Huawei Noah's Ark Lab) · Xueyi Zou (Huawei Noah's Ark Lab) · Henghui Ding (ETH Zurich) · Yulun Zhang (ETH Zurich) · Radu Timofte () · Luc Van Gool (ETH Zurich)

Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance
Heeseung Kim (Seoul National University) · Sungwon Kim (Seoul National University) · Sungroh Yoon (Seoul National University)

Safe Exploration for Efficient Policy Evaluation and Comparison
Runzhe Wan (Amazon) · Branislav Kveton (Google Research) · Rui Song (North Carolina State University)

Structural Entropy Guided Graph Hierarchical Pooling
Junran Wu (State Key Lab of Software Development Environment, Beihang University) · Xueyuan Chen (Beihang University) · Shangzhe Li (beihang university) · Ke Xu (Beihang University)

You Only Cut Once: Boosting Data Augmentation with a Single Cut
Junlin Han (CSIRO) · Pengfei Fang (The Australian National University) · Weihao Li (Data61, CSIRO) · Jie Hong (Australian National University) · Mohammad Ali Armin (CSIRO(Data61)) · Ian Reid ("University of Adelaide, Australia") · Lars Petersson (Data61/CSIRO) · HONGDONG LI (Australian National University, Australia)

Channel Importance Matters in Few-Shot Image Classification
Xu Luo (University of Electronic Science and Technology of China) · Jing Xu (Harbin Institute of Technology, Shenzhen) · ZENGLIN Xu (Harbin Institute of Technology, Shenzhen)

Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization
Minghuan Liu (Shanghai Jiao Tong University) · Zhengbang Zhu (Shanghai Jiao Tong University) · Yuzheng Zhuang (HUAWEI) · Weinan Zhang (Shanghai Jiao Tong University) · Jianye Hao (Huawei Noah's Ark Lab) · Yong Yu (Shanghai Jiao Tong University) · Jun Wang (UCL)

$p$-Laplacian Based Graph Neural Networks
Guoji Fu (Tencent AI Lab) · Peilin Zhao (Tencent AI Lab) · Yatao Bian (Tencent AI Lab)

SDQ: Stochastic Differentiable Quantization with Mixed Precision
Xijie Huang (HKUST) · Zhiqiang Shen (Carnegie Mellon University) · Shichao Li (Hong Kong University of Science and Technology) · Zechun Liu (Carnegie Mellon University) · Hu Xianghong (HKUST) · Jeffry Wicaksana (Hong Kong University of Science and Technology) · Eric Xing (Petuum Inc. and CMU) · Kwang-Ting Cheng (Hong Kong University of Science and Technology)

Off-Policy Evaluation for Large Action Spaces via Embeddings
Yuta Saito (Cornell University) · Thorsten Joachims (Cornell)

Generalized Strategic Classification and the Case of Aligned Incentives
Sagi Levanon (Technion) · Nir Rosenfeld (Technion)

AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems
Wenzheng Hou (Institute of Computing Technology) · Qianqian Xu (Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences) · zhiyong yang (中国科学院大学) · Shilong Bao (SKLOIS, Institute of Information Engineering, Chinese Academy of Sciences; SCS, University of CAS) · Yuan He (Alibaba Group) · Qingming Huang (University of Chinese Academy of Sciences)

Strategic Representation
Vineet Nair (Technion) · Ganesh Ghalme (Indian Institute of Technology, Hyderabad) · Inbal Talgam-Cohen (Technion) · Nir Rosenfeld (Technion)

Principled Knowledge Extrapolation with GANs
Ruili Feng (USTC) · Jie Xiao (University of Science and Technology of China) · Kecheng Zheng (University of Science and Technology of China) · Deli Zhao (Alibaba Group) · Jingren Zhou (Alibaba Group) · Qibin Sun (University of Science and Technology of China) · Zheng-Jun Zha (University of Science and Technology of China)

Bayesian Deep Embedding Topic Meta-Learner
Zhibin Duan (Xidian University) · Yishi Xu (Xidian University) · Jianqiao Sun (Xidian University) · Bo Chen (School of Electronic Engineering, Xidian University) · Wenchao Chen (Xi'dian University) · CHAOJIE WANG (XIDIAN UNIVERSITY) · Mingyuan Zhou (University of Texas at Austin)

Adversarial Attacks on Gaussian Process Bandits
Eric Han (National University of Singapore, School of Computing) · Jonathan Scarlett (National University of Singapore)

NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning
Wentao Zhang (Peking University) · Zeang Sheng (Peking University) · Mingyu Yang (Peking University) · Yang Li (Peking University) · Yu Shen (Peking University) · Zhi Yang (Peking University) · Bin Cui (Peking University)

Nearly Optimal Policy Optimization with Stable at Any Time Guarantee
Tianhao Wu (UC Berkeley) · Yunchang Yang (Peking University) · Han Zhong (Peking University) · Liwei Wang (Peking University) · Simon Du (University of Washington) · Jiantao Jiao (University of California, Berkeley)

VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix
Teng Wang (Southern University of Science and Technology) · Wenhao Jiang (Tencent) · Zhichao Lu (Southern University of Science and Technology) · Feng Zheng (SUSTech) · Ran Cheng (Southern University of Science and Technology) · chengguo yin (tencent) · Ping Luo (The University of Hong Kong)

Multi-Level Branched Regularization for Federated Learning
Jinkyu Kim (Seoul National University) · Geeho Kim (Seoul National University) · Bohyung Han (Seoul National University)

Personalized Federated Learning via Variational Bayesian Inference
Xu Zhang (Chinese Academy of Sciences) · Yinchuan Li (Huawei Noah’s Ark Lab) · Wenpeng Li (Huawei Noah's Ark Lab) · Kaiyang Guo (Noah's Ark Lab, Huawei Technologies) · Yunfeng Shao (Huawei Noah's Ark Lab)

On the Practicality of Deterministic Epistemic Uncertainty
Janis Postels (ETH Zurich) · Mattia Segù (ETH Zurich) · Tao Sun (ETH Zurich) · Luca Daniel Sieber (ETH Zurich) · Luc Van Gool (ETH Zurich) · Fisher Yu (ETH Zurich) · Federico Tombari (Google, TU Munich)

Achieving Fairness at No Utility Cost via Data Reweighing
Peizhao Li (Brandeis University) · Hongfu Liu (Brandeis University)

Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Lukas Struppek (Technical University of Darmstadt) · Dominik Hintersdorf (Technical University of Darmstadt) · Antonio De Almeida Correia (Technical University of Darmstadt) · Antonia Adler (Universität der Bundeswehr (München)) · Kristian Kersting (TU Darmstadt)

On Non-local Convergence Analysis of Deep Linear Networks
Kun Chen (Peking University) · Dachao Lin (Peking University) · Zhihua Zhang (Peking University)

HousE: Knowledge Graph Embedding with Householder Parameterization
Rui Li (Dalian University of Technology) · Jianan Zhao (University of Notre Dame) · Chaozhuo Li (Microsoft Research Asia) · Di He (Microsoft Research) · Yiqi Wang (Michigan State University) · Yuming Liu (Microsoft) · Hao Sun (Microsoft) · Senzhang Wang (Central South University) · Weiwei Deng (Microsoft) · Yanming Shen (Dalian University of Technology) · Xing Xie (Microsoft Research Asia) · Qi Zhang (Microsoft)

Robust Multi-Objective Bayesian Optimization Under Input Noise
Samuel Daulton (Meta, University of Oxford) · Sait Cakmak (Meta) · Maximilian Balandat (Facebook) · Michael A Osborne (U Oxford) · Enlu Zhou () · Eytan Bakshy (Meta)

Convolutional and Residual Networks Provably Contain Lottery Tickets
Rebekka Burkholz (CISPA, Helmholtz Center, Saarland Informatics Campus)

Stabilizing Off-Policy Deep Reinforcement Learning from Pixels
Edoardo Cetin (King's College London) · Philip Ball (University of Oxford) · Stephen Roberts (University of Oxford) · Oya Celiktutan (King's College London)

A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks
Yu Pan (Harbin Institute of Technology, Shenzhen) · Zeyong Su (University of Electronic Science and Technology of China) · Ao Liu (Tokyo Institute of Technology) · Jingquan Wang (Harbin Institute of Technology, Shenzhen) · Nannan Li (Institute of Automation, Chinese Academy of Sciences,University of Chinese Academy of Sciences) · ZENGLIN Xu (Harbin Institute of Technology, Shenzhen)

Balancing Discriminability and Transferability for Source-Free Domain Adaptation
Jogendra Nath Kundu (Indian Institute of Science) · Akshay Kulkarni (Indian Institute of Science) · Suvaansh Bhambri (Indian Institute of Science) · Deepesh Mehta (Indian Institute of Science) · Shreyas Kulkarni (Indian Institute of Science) · Varun Jampani (Google Research) · Venkatesh Babu Radhakrishnan (Indian Institute of Science)

PMIC: Improving Multi-Agent Reinforcement Learning with ProgressiveMutual Information Collaboration
Pengyi Li (Tianjin university) · Hongyao Tang (Tianjin University) · Tianpei Yang (University of Alberta) · Xiaotian Hao (College of Intelligence and Computing, Tianjin University) · Tong Sang (Tianjin University) · Yan Zheng (Tianjin University, Nanyang Technical University) · Jianye Hao (Tianjin University) · Matthew Taylor (U. of Alberta) · Wenyuan Tao (Tianjin University) · Zhen Wang (Northwestern Polytechnical University)

Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
Ting-Han Fan (Princeton University) · Ta-Chung Chi (Carnegie Mellon University) · Alexander Rudnicky (Carnegie Mellon University) · Peter Ramadge (Princeton)

Preconditioning for Scalable Gaussian Process Hyperparameter Optimization
Jonathan Wenger (University of Tübingen) · Geoff Pleiss (Columbia University) · Philipp Hennig (University of Tuebingen) · John Cunningham (Columbia) · Jacob Gardner (University of Pennsylvania)

Generative Flow Networks for Discrete Probabilistic Modeling
Dinghuai Zhang (Mila, Meta) · Nikolay Malkin (Mila / Université de Montréal) · Zhen Liu (Mila, University of Montreal) · Alexandra Volokhova (Moscow Institute of Physics and Technology) · Aaron Courville (Université de Montréal) · Yoshua Bengio (Mila - Quebec AI Institute)

Closed-Form Diffeomorphic Transformations for Time Series Alignment
Iñigo Martinez (Vicomtech) · Elisabeth Viles (University of Navarra-School of Engineering) · Igor G. Olaizola (Vicomtech)

Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
Mark Collier (Google) · Rodolphe Jenatton (Google Research) · Efi Kokiopoulou (Google AI) · Jesse Berent (Google)

Minimum Cost Intervention Design for Causal Effect Identification
Sina Akbari (École Polytechnique Fédérale de Lausanne (EPFL)) · Jalal Etesami (EPFL) · Negar Kiyavash (École Polytechnique Fédérale de Lausanne)

Codeformer: Learning to Translate from C to CUDA
Yuanbo Wen (Institute of Computing Technology, Chinese Academy of Sciences) · Qi Guo (Institute of Computing Technology, Chinese Academy of Sciences) · Qiang Fu (USTC) · XiaQing Li (Institute of Computing Technology, Chinese Academy of Science) · jianxing xu (School of Computer Science and Technology, University of Science and Technology of China) · Yanlin Tang (Institute of Computing Technology, Chinese Academy of Sciences) · Yongwei Zhao (Institute of Computing Technology, Chonese Academy of Sciences) · Xing Hu (Institute of Computing Technology) · Zidong Du (institute of Computing Technology of the Chinese Academy of Sciences) · Ling Li (Institute of Software, Chinese Academy of Sciences) · Chao Wang (USTC) · Xuehai Zhou (University of Science and Technology of China) · Yunji Chen (Institute of Computing Technology, Chinese Academy of Sciences)

Stable Conformal Prediction Sets
Eugene Ndiaye (Georgia Tech)

Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks
Runpei Dong (Xi'an Jiaotong University) · Zhanhong Tan (Tsinghua University) · Mengdi Wu (Tsinghua University) · Linfeng Zhang (Tsinghua University ) · Kaisheng Ma (Tsinghua University )

Delayed Reinforcement Learning by Imitation
Pierre Liotet (Politecnico di Milano) · Davide Maran (Politecnico di Milano) · Lorenzo Bisi (Politecnico di Milano) · Marcello Restelli (Politecnico di Milano)

Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
Keegan Harris (Carnegie Mellon University) · Dung Ngo (University of Minnesota) · Logan Stapleton (University of Minnesota) · Hoda Heidari (CMU) · Steven Wu (Carnegie Mellon University)

Predicting Out-of-Distribution Error with the Projection Norm
Yaodong Yu (University of California, Berkeley) · Zitong Yang (University of California, Berkeley) · Alexander Wei (UC Berkeley) · Yi Ma (UC Berkeley) · Jacob Steinhardt (UC Berkeley)

Inductive Matrix Completion: No Bad Local Minima and a Fast Algorithm
Pini Zilber (Weizmann Institute of Science) · Boaz Nadler (Weizmann Institute of Science)

SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals
Dani Kiyasseh (California Institute of Technology) · Tingting Zhu (University of Oxford) · David Clifton (University of Oxford)

Bounding Training Data Reconstruction in Private (Deep) Learning
Chuan Guo (Meta AI) · Brian Karrer (Meta) · Kamalika Chaudhuri (UCSD and Facebook AI Research) · Laurens van der Maaten (Facebook AI Research)

Improving Out-of-Distribution Robustness via Selective Augmentation
Huaxiu Yao (Stanford University) · Yu Wang (University of Science and Technology of China) · Sai Li (Renmin University of China) · Linjun Zhang (Rutgers University) · Weixin Liang (Stanford University) · James Zou (Stanford University) · Chelsea Finn (Stanford)

Adversarial Masking for Self-Supervised Learning
Yuge Shi (University of Oxford) · Siddharth N (University of Edinburgh) · Phil Torr (Oxford) · Adam Kosiorek (DeepMind)

Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning
Sattar Vakili (MediaTek Research) · Jonathan Scarlett (National University of Singapore) · Da-shan Shiu (MediaTek Research) · Alberto Bernacchia (MediaTek Research)

Nesterov Accelerated Shuffling Gradient Method for Convex Optimization
Trang Tran (Cornell University) · Lam Nguyen (IBM Research, Thomas J. Watson Research Center) · Katya Scheinberg (Cornell University)

Monarch: Expressive Structured Matrices for Efficient and Accurate Training
Tri Dao (Stanford) · Beidi Chen (Stanford University) · Nimit Sohoni (Stanford University) · Arjun Desai (Stanford University) · Michael Poli (Stanford University) · Jessica Grogan (University at Buffalo) · Alexander Liu (University of Michigan) · Aniruddh Rao (University of Michigan) · Atri Rudra (University at Buffalo, SUNY) · Christopher Re (Stanford University)

SkexGen: Generating CAD Construction Sequences by Autoregressive VAE with Disentangled Codebooks
Xiang Xu (Simon Fraser University) · Karl Willis (Autodesk Research) · Joseph G Lambourne (Autodesk AI Lab) · Chin-Yi Cheng (Google Research) · Pradeep Kumar Jayaraman (Autodesk Research) · Yasutaka Furukawa (Simon Fraser University)

Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness
Namuk Park (NAVER AI Lab) · Songkuk Kim (Yonsei University)

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Junnan Li (Salesforce) · DONGXU LI (Salesforce) · Caiming Xiong (Salesforce) · Steven Hoi (Salesforce)

A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization
Renzhe Xu (Tsinghua University) · Peng Cui (Tsinghua University) · Zheyan Shen (Tsinghua University) · Xingxuan Zhang (Tsinghua University) · Tong Zhang (HKUST)

DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting
Shiyong Lan (College of Computer Science, Sichuan University, Chengdu, China.) · Yitong Ma (Sichuan University) · Weikang Huang (National Key Laboratory of Fundamental Science on Synthetic Vision) · Wenwu Wang (University of Surrey) · Hongyu Yang (Sichuan University) · pyang li (四川大学)

Online Learning and Pricing with Reusable Resources: Linear Bandit with Sub-exponential Rewards
Huiwen Jia (IOE, University of Michigan, Ann Arbor) · Cong Shi (University of Michigan at Ann Arbor) · Siqian Shen (University of Michigan)

Accelerating Shapley Explanation via Contributive Cooperator Selection
Guanchu Wang (Rice University) · Yu-Neng Chuang (Rice University) · Mengnan Du (Texas A&M University) · Fan Yang (Rice University) · Quan Zhou (Meta) · Pushkar Tripathi (Meta) · Xuanting Cai (Meta) · Xia Hu (Rice University)

Exact Optimal Accelerated Complexity for Fixed-Point Iterations
Jisun Park (Seoul National University) · Ernest Ryu (Seoul National University)

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
Sixing Yu (Iowa State University) · Ali Jannesari (Iowa State University) · Arya Mazaheri (Technische Universität Darmstadt)

Efficient PAC Learning from the Crowd with Pairwise Comparisons
Jie Shen (Stevens Institute of Technology) · Shiwei Zeng (Stevens Institute of Technology)

Metric-Fair Active Learning
Nan Cui (Stevens Institute of Technology) · Jie Shen (Stevens Institute of Technology) · Jing Wang (Amazon)

Black-Box Tuning for Language-Model-as-a-Service
Tianxiang Sun (Fudan University) · Yunfan Shao (Fudan University) · Hong Qian (East China Normal University) · Xuanjing Huang (Fudan University) · Xipeng Qiu (Fudan University)

Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring
Zhengquan Luo (University of Science and Technology of China & Institute of Automation, Chinese Academy of Sciences) · Yunlong Wang (Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR) Institute of Automation, Chinese Academy of Sciences (CASIA) ) · Zilei Wang (University of Science and Technology of China) · Zhenan Sun (Chinese of Academy of Sciences) · Tieniu Tan (NLPR, China)

Confidence Score for Source-Free Unsupervised Domain Adaptation
Jonghyun Lee (Seoul National University) · Dahuin Jung (Seoul National University) · Junho Yim (AIRS Company, Hyundai Motor Group) · Sungroh Yoon (Seoul National University)

Continuous-Time Analysis of Accelerated Gradient Methods via Conservation Laws in Dilated Coordinate Systems
Jaewook Suh (Seoul National University) · Gyumin Roh (Seoul National University) · Ernest Ryu (Seoul National University)

Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations
Jaehyeong Jo (KAIST) · Seul Lee (KAIST) · Sung Ju Hwang (KAIST, AITRICS)

Denoised MDPs: Learning World Models Better Than the World Itself
Tongzhou Wang (MIT) · Simon Du (University of Washington) · Antonio Torralba (MIT) · Phillip Isola (MIT) · Amy Zhang (FAIR / UC Berkeley) · Yuandong Tian (Facebook AI Research)

On the Finite-Time Performance of the Knowledge Gradient Algorithm
Yanwen Li (City University of Hong Kong) · Siyang Gao (City University of Hong Kong)

REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer
Xingyu Liu (Carnegie Mellon University) · Deepak Pathak (Carnegie Mellon University) · Kris Kitani (Carnegie Mellon University)

PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs
Zhengyang Shen (Peking University) · Tao Hong (Peking University) · Qi She (Bytedance) · Jinwen Ma (Peking University) · Zhouchen Lin (Peking University)

Neuro-Symbolic Hierarchical Rule Induction
Claire Glanois (IT University Copenhagen) · Zhaohui Jiang (Shanghai Jiao Tong University) · Xuening Feng (Shanghai Jiao Tong University) · Paul Weng (Shanghai Jiao Tong University) · Matthieu Zimmer (Shanghai Jiao Tong University) · Dong Li (Huawei Noah's Ark Lab) · Wulong Liu (Huawei Noah's Ark Lab) · Jianye Hao (Huawei Noah's Ark Lab)

Hierarchical Few-Shot Generative Models
Giorgio Giannone (Technical University of Denmark (DTU)) · Ole Winther (DTU and KU)

Learning Stable Classifiers by Transferring Unstable Features
Yujia Bao (MIT) · Shiyu Chang (UCSB) · Regina Barzilay (MIT CSAIL)

NP-Match: When Neural Processes meet Semi-Supervised Learning
Jianfeng Wang (University of Oxford) · Thomas Lukasiewicz (TU Wien and University of Oxford) · Xiaolin Hu (Tsinghua University) · Daniela Massiceti (Microsoft Research) · Vladimir Pavlovic (Rutgers University / Samsung AI Center) · Alexandros Neophytou (Microsoft)

A Study of Face Obfuscation in ImageNet
Kaiyu Yang (Princeton University) · Jacqueline Yau (Stanford University) · Li Fei-Fei (Stanford University) · Jia Deng (Princeton University) · Olga Russakovsky (Princeton University)

Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing
Ramji Venkataramanan (University of Cambridge) · Kevin Kögler (IST Austria) · Marco Mondelli (IST Austria)

Recurrent Model-Free RL can be a Strong Baseline for Many POMDPs
Tianwei Ni (Université de Montréal) · Benjamin Eysenbach (Carnegie Mellon University) · Ruslan Salakhutdinov (Carnegie Mellen University)

Self-Supervised Representation Learning via Latent Graph Prediction
Yaochen Xie (Texas A&M University) · Zhao Xu (Texas A&M University) · Shuiwang Ji (Texas A&M University)

Choosing Answers in Epsilon-Best-Answer Identification for Linear Bandits
Marc Jourdan (Inria, Universite de Lille) · Rémy Degenne (Inria Lille)

Detached Error Feedback for Distributed SGD with Random Sparsification
An Xu (University of Pittsburgh) · Heng Huang (University of Pittsburgh & JD Finance America Corporation)

Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification
Peter J. Bevan (Newcastle University) · Amir Atapour-Abarghouei (Durham University)

Faster Algorithms for Learning Convex Functions
Ali Siahkamari (Boston University) · Durmus Alp Emre Acar (Boston University) · Christopher Liao (Boston University) · Kelly Geyer (Boston University) · Venkatesh Saligrama (Boston University) · Brian Kulis (Boston University and Amazon)

Hermite Polynomial Features for Private Data Generation
Margarita Vinaroz (Max Planck Institute for Intelligent Systems and University of Tuebingen) · Mohammad-Amin Charusaie (Max-Planck-Institute for Intelligent Systems) · Frederik Harder (Max Planck Institute) · Kamil Adamczewski (Max Planck Institute for Intelligent Systems) · Mi Jung Park (UBC)

Large-Scale Graph Neural Architecture Search
Chaoyu Guan (Tsinghua University) · Xin Wang (Tsinghua University) · Hong Chen (Tsinghua University) · Ziwei Zhang (Tsinghua University) · Wenwu Zhu (Tsinghua University)

Meaningfully debugging model mistakes using conceptual counterfactual explanations
Abubakar Abid (Stanford) · Mert Yuksekgonul (Stanford University) · James Zou (Stanford)

Understanding Policy Gradient Algorithms: A Sensitivity-Based Approach
Shuang Wu (Huawei Noah's Ark Lab) · Ling Shi (The Hong Kong University of Science and Technology) · Jun Wang (UCL) · Guangjian Tian (Huawei Noah’s Ark Lab)

Unaligned Supervision for Automatic Music Transcription in The Wild
Ben Maman (Tel Aviv University) · Amit Bermano (Tel-Aviv University)

Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations
Haoran Xu (Xidian University) · Xianyuan Zhan (Tsinghua University) · Honglei Yin (JD Intelligent Cities Research) · Huiling qin (Xidian University)

Model Agnostic Sample Reweighting for Out-of-Distribution Learning
Xiao Zhou (HKUST) · Yong LIN (The Hong Kong University of Science and Technology) · Renjie Pi (Hong Kong University of Science and Technology) · Weizhong Zhang (The Hong Kong University of Science and Technology) · Renzhe Xu (Tsinghua University) · Peng Cui (Tsinghua University) · Tong Zhang (HKUST)

Probabilistic Bilevel Coreset Selection
Xiao Zhou (HKUST) · Renjie Pi (Hong Kong University of Science and Technology) · Weizhong Zhang (The Hong Kong University of Science and Technology) · Yong LIN (The Hong Kong University of Science and Technology) · Zonghao Chen (Tsinghua University) · Tong Zhang (HKUST)

Benchmarking and Analyzing Point Cloud Classification under Corruptions
Jiawei Ren (Nanyang Technological University) · Liang Pan (Nanyang Technological University) · Ziwei Liu (Nanyang Technological University)

Equivariant graph neural networks with complete local frames
weitao du (University of science and technology of china) · He Zhang (Xi'an Jiaotong University) · Yuanqi Du (George Mason University) · Qi Meng (Microsoft) · Wei Chen (Chinese Academy of Sciences) · Tie-Yan Liu (Microsoft Research Asia) · Nanning Zheng (Xi'an Jiaotong University) · Bin Shao (Microsoft Research Asia)

Going Deeper into Permutation-Sensitive Graph Neural Networks
Zhongyu Huang (Institute of Automation, Chinese Academy of Sciences) · Yingheng Wang (Johns Hopkins University) · Chaozhuo Li (Microsoft Research Asia) · Huiguang He (Institute of Automation, Chinese Academy of Sciences)

Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
Kendrick Shen (Stanford University) · Robbie Jones (Stanford University) · Ananya Kumar (Stanford University) · Sang Michael Xie (Stanford University) · Jeff Z. HaoChen (Stanford University) · Tengyu Ma (Stanford University) · Percy Liang (Stanford University)

Diversified Adversarial Attacks based on Conjugate Gradient Method
Keiichiro Yamamura (Kyushu University) · Haruki Sato (Kyushu University) · Nariaki Tateiwa (NTT Corporation) · Nozomi Hata (Kyushu University) · Katsuki Fujisawa (Kyushu University) · Issa Oe (Kyushu University) · Hiroki Ishikura (Kyushu University) · Toru Mitsutake (Kyushu University)

On the Effects of Artificial Data Modification
Antonia Marcu (University of Southampton) · Adam Prugel-Bennett (apb@ecs.soton.ac.uk)

COLA: Consistent Learning with Opponent-Learning Awareness
Timon Willi (University of Oxford) · Alistair Letcher (None) · Johannes Treutlein (University of Toronto, Vector Institute) · Jakob Foerster (Oxford university)

Scalable Deep Gaussian Markov Random Fields for General Graphs
Joel Oskarsson (Linköping University) · Per Sidén (Linköping University) · Fredrik Lindsten (Linköping University)

DNA: Domain Generalization with Diversified Neural Averaging
Xu Chu (Tsinghua University) · Yujie Jin (Peking University) · Wenwu Zhu (Tsinghua University) · Yasha Wang (Peking University) · Shanghang Zhang (UC Berkeley) · Xin Wang (Tsinghua University) · Hong Mei (Peking University)

Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis
Sho Sonoda (RIKEN AIP) · Isao Ishikawa (Center for Data Science, Ehime University) · Masahiro Ikeda (RIKEN AIP)

Adversarial Attacks and Defenses for Non-Parametric Two-Sample Tests
Xilie Xu (National University of Singapore) · Jingfeng Zhang (RIKEN) · Feng Liu (The University of Melbourne) · Masashi Sugiyama (RIKEN / The University of Tokyo) · Mohan Kankanhalli (National University of Singapore,)

Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs
Jie Ren (Shanghai Jiao Tong University) · Mingjie Li (Shanghai Jiao Tong University) · Meng Zhou (Carnegie Mellon University) · Shih-Han Chan (University of California San Diego) · Quanshi Zhang (Shanghai Jiao Tong University)

Auxiliary Learning with Joint Task and Data Scheduling
Hong Chen (Tsinghua University) · Xin Wang (Tsinghua University) · Chaoyu Guan (Tsinghua University) · Yue Liu (Tsinghua University) · Wenwu Zhu (Tsinghua University)

Fishr: Invariant Gradient Variances for Out-of-distribution Generalization
Alexandre Rame (Sorbonne University) · Corentin Dancette (LIP6) · Matthieu Cord (Sorbonne University)

Towards Uniformly Superhuman Autonomy via Subdominance Minimization
Brian Ziebart (University of Illinois at Chicago) · Sanjiban Choudhury (Aurora) · Xinyan Yan (Aurora Innovation) · Paul Vernaza (Aurora Innovation)

Information Discrepancy in Strategic Learning
Yahav Bechavod (Hebrew University) · Chara Podimata (Harvard University) · Steven Wu (Carnegie Mellon University) · Juba Ziani (University of Pennsylvania)

On the Convergence of Inexact Predictor-Corrector Methods for Linear Programming
Gregory Dexter (Purdue University) · Agniva Chowdhury (Oak Ridge National Laboratory) · Haim Avron (Tel Aviv University) · Petros Drineas (Purdue University)

In defense of dual-encoders for neural ranking
Aditya Menon (Google Research) · Sadeep Jayasumana (Google Research) · Ankit Singh Rawat (Google) · Seungyeon Kim (Google Research) · Sashank Jakkam Reddi (Google) · Sanjiv Kumar (Google Research, NY)

Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
Haotao Wang (University of Texas at Austin) · Aston Zhang (Amazon AI) · Yi Zhu (Amazon) · Shuai Zheng (Amazon Web Services) · Mu Li () · Alex Smola (Amazon) · Zhangyang “Atlas” Wang (University of Texas at Austin)

GenLabel: Mixup Relabeling using Generative Models
Jy yong Sohn (University of Wisconsin-Madison) · Liang Shang (University of Wisconsin-Madison) · Hongxu Chen (University of Wisconsin-Madison) · Jaekyun Moon (KAIST) · Dimitris Papailiopoulos (University of Wisconsin-Madison) · Kangwook Lee (UW Madison)

Be Like Water: Adaptive Floating Point for Machine Learning
Thomas Y. Yeh (Pomona College) · Alexander Ihler (UC Irvine) · Maxwell Sterner (Luminous Computing) · Zerlina Lai (Occidental College) · Brandon Chuang (UC Santa Cruz)

Online Decision Transformer
Qinqing Zheng (Meta AI Research) · Amy Zhang (FAIR / UC Berkeley) · Aditya Grover (UCLA)

Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization
Giuseppe Bruno De Luca (Stanford) · Eva Silverstein (Stanford University)

Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning
Utku Evci (Google) · Vincent Dumoulin (Google) · Hugo Larochelle (Google Brain) · Michael Mozer (Google Research)

Building Robust Ensembles via Margin Boosting
Dinghuai Zhang (Mila, Meta) · Hongyang Zhang (University of Waterloo) · Aaron Courville (Université de Montréal) · Yoshua Bengio (Mila - Quebec AI Institute) · Pradeep Ravikumar (Carnegie Mellon University) · Arun Sai Suggala (Carnegie Mellon University)

Graph Neural Architecture Search Under Distribution Shifts
Yijian Qin (Tsinghua University) · Xin Wang (Tsinghua University) · Ziwei Zhang (Tsinghua University) · Pengtao Xie (UC San Diego) · Wenwu Zhu (Tsinghua University)

Matching Structure for Dual Learning
Hao Fei (National University of Singapore) · Shengqiong Wu (National University of Singapore) · Yafeng Ren (Guangdong University of Foreigh Studies) · Meishan Zhang (Harbin Institute of Technology (Shenzhen))

Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity
Jianyi Yang (UC Riverside) · Shaolei Ren (UCR)

ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases
Jintai Chen (Zhejiang University) · KuanLun Liao (Zhejiang University) · Kun Wei (Xidian University) · Haochao Ying (Zhejiang University) · Danny Z Chen (University of Notre Dame) · Jian Wu (Zhejiang University)

Self-supervised Models are Good Teaching Assistants for Vision Transformers
Haiyan Wu (East China Normal University) · Yuting Gao (Tencent) · Yinqi Zhang (Jinan University) · Shaohui Lin (East China Normal University) · Yuan Xie (East China Normal University) · Xing Sun (Tencent) · Ke Li (Tencent)

Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding
Haotian Ma (Southern University of Science and Technology) · Hao Zhang (Shanghai Jiao Tong University) · Fan Zhou (Shanghai Jiao Tong University) · Yinqing Zhang (Shanghai Jiao Tong University) · Quanshi Zhang (Shanghai Jiao Tong University)

Understanding Robust Overfitting of Adversarial Training and Beyond
Chaojian Yu (The University of Sydney) · Bo Han (HKBU / RIKEN) · Li Shen (JD Explore Academy) · Jun Yu (University of Science and Technology of China) · Chen Gong (Nanjing University of Science and Technology) · Mingming Gong (University of Melbourne) · Tongliang Liu (The University of Sydney)

A Minimax Learning Approach to Off-Policy Evaluation in Partially Observable Markov Decision Processes
Chengchun Shi (London School of Economics and Political Science) · Masatoshi Uehara (Cornell University) · Jiawei Huang (University of Illinois at Urbana-Champaign) · Nan Jiang (University of Illinois at Urbana-Champaign)

Flowformer: Linearizing Transformers with Conservation Flows
Haixu Wu (Tsinghua University) · Jialong Wu (Tsinghua University) · Jiehui Xu (THU) · Jianmin Wang (Tsinghua University) · Mingsheng Long (Tsinghua University)

Mirror Learning: A Unifying Framework of Policy Optimisation
Jakub Grudzien Kuba (University of Oxford) · Christian Schroeder de Witt (University of Oxford) · Jakob Foerster (Oxford university)

Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks
Noam Razin (Tel Aviv University) · Asaf Maman (Tel Aviv University) · Nadav Cohen (Tel Aviv University)

Value Function based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems
Lucy Gao (University of Waterloo) · Jane J. Ye (University of Victoria) · Haian Yin (Southern University of Science and Technology) · Shangzhi Zeng (University of Victoria) · Jin Zhang (Southern University of Science and Technology)

Scalable Spike-and-Slab
Niloy Biswas (Harvard University) · Lester Mackey (Microsoft Research) · Xiao-Li Meng (Harvard University)

Conditional GANs with Auxiliary Discriminative Classifier
Liang Hou (Institute of Computing Technology, Chinese Academy of Sciences) · Qi Cao (Institute of Computing Technology, Chinese Academy of Sciences) · Huawei Shen (Institute of Computing Technology, Chinese Academy of Sciences) · Siyuan Pan (Shanghai Jiao Tong University) · Xiaoshuang Li (Shanghai Jiao Tong University) · Xueqi Cheng (Institute of Computing Technology, CAS, China)

Anarchic Federated Learning
Haibo Yang (The Ohio State University) · Xin Zhang (Iowa State University) · Prashant Khanduri (University Of Minnesota) · Jia Liu (The Ohio State University)

Surrogate Likelihoods for Variational Annealed Importance Sampling
Martin Jankowiak (Broad Institute / Basis) · Du Phan (Google)

Decomposing Temporal High-Order Interactions via Latent ODEs
Shibo Li (University of Utah) · Robert Kirby (University of Utah) · Shandian Zhe (University of Utah)

Contextual Information-Directed Sampling
Botao Hao (Deepmind) · Tor Lattimore (DeepMind) · Chao Qin (Columbia University)

PAC-Bayesian Bounds on Rate-Efficient Classifiers
Alhabib Abbas (University College London) · Yiannis Andreopoulos (University College London)

Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks
Weiran Lin (Carnegie Mellon University) · Keane Lucas (Carnegie Mellon University) · Lujo Bauer (Carnegie Mellon University) · Michael Reiter (Duke University) · Mahmood Sharif (Tel Aviv University)

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
Laixi Shi (Carnegie Mellon University) · Gen Li (Tsinghua University, China) · Yuting Wei (University of Pennsylvania) · Yuxin Chen (University of Pennsylvania) · Yuejie Chi (CMU)

Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
Anqi Zhang (New York University) · Jinkun Lin (New York University) · Aurojit Panda (NYU) · Jinyang Li (New York University) · Mathias Lécuyer (University of British Columbia) · Siddhartha Sen (Microsoft Research)

Fast-Rate PAC-Bayesian Generalization Bounds for Meta-Learning
Jiechao Guan (Renmin University of China) · Zhiwu Lu (Renmin University of China)

Multi Resolution Analysis (MRA) for Approximate Self-Attention
Zhanpeng Zeng (University of Wisconsin-Madison) · Sourav Pal (University of Wisconsin - Madison) · Jeffery Kline (American Family Insurance) · Glenn Fung (American Family Insurance) · Vikas Singh (University of Wisconsin Madison)

Visual Attention Emerges from Recurrent Sparse Reconstruction
Baifeng Shi (UC Berkeley) · Yale Song (Microsoft Research) · Neel Joshi (MICROSOFT RESEARCH) · Xin Wang (Microsoft Research, Redmond) · Trevor Darrell (University of California at Berkeley)

Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization
Xiang Gao (School of Computer Science and Technology, University of Chinese Academy of Sciences) · Yuqi Zhang (University of Chinese Academy of Sciences) · Yingjie Tian (University of Chinese Academy of Sciences)

Neurotoxin: Durable Backdoors in Federated Learning
Zhengming Zhang (Southeast University) · Ashwinee Panda (Princeton University) · Linyue Song (University of California, Berkeley) · Yaoqing Yang (UC Berkeley) · Michael Mahoney (UC Berkeley) · Prateek Mittal (Princeton University) · Kannan Ramchandran (UC Berkeley) · Joseph E Gonzalez (UC Berkeley)

Faster Fundamental Graph Algorithms via Learned Predictions
Justin Chen (MIT) · Sandeep Silwal (MIT) · Ali Vakilian (Toyota Technological Institute at Chicago) · Fred Zhang (UC Berkeley)

Understanding The Robustness in Vision Transformers
Zhou Daquan (National University of Singapore, Insititute of Data Science, Learning and Vision Lab) · Zhiding Yu (NVIDIA) · Enze Xie (The University of Hong Kong) · Chaowei Xiao (University of Michigan) · Animashree Anandkumar (Caltech and NVIDIA) · Jiashi Feng (ByteDance) · Jose M. Alvarez (Nvidia)

Efficient Test-Time Model Adaptation without Forgetting
Shuaicheng Niu (South China University of Technology) · Jiaxiang Wu (Tencent AI Lab) · Yifan Zhang (National University of Singapore) · Yaofo Chen (South China University of Technology) · Shijian Zheng (South China University of Technology) · Peilin Zhao (Tencent AI Lab) · Mingkui Tan (South China University of Technology)

Identity-Disentangled Adversarial Augmentation for Self-supervised Learning
Kaiwen Yang (University of Science and Technology of China) · Tianyi Zhou (University of Washington) · Xinmei Tian (University of Science and Technology of China) · Dacheng Tao ()

Approximate Frank-Wolfe Algorithms over Graph-structured Support Sets
Baojian Zhou (Fudan University) · Yifan Sun (Stony Brook University)

Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning
Lipeng Wan (Xian Jiaotong University) · Zeyang Liu (Xi'an Jiaotong University) · Xingyu Chen (Xi'an Jiaotong University) · Xuguang Lan () · Nanning Zheng (Xi'an Jiaotong University)

Large Batch Experience Replay
Thibault Lahire (Université de Toulouse, ISAE-SUPAERO) · Matthieu Geist (Google) · Emmanuel Rachelson (ISAE-SUPAERO)

ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training
Hui-Po Wang (CISPA Helmholtz Center for Information Security) · Sebastian Stich (CISPA Helmholtz Center for Information Security gGmbH) · Yang He (Amazon) · Mario Fritz (CISPA Helmholtz Center for Infomation Security)

Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
Jing Lin (Tsinghua Univisity, Tsinghua Shenzhen International Graduate School) · Xiaowan Hu (Tsinghua Univisity, Tsinghua Shenzhen International Graduate School) · Yuanhao Cai (Tsinghua Univisity, Tsinghua Shenzhen International Graduate School) · Haoqian Wang (Tsinghua Shenzhen International Graduate School, Tsinghua University) · Youliang Yan (Huawei Noah's Ark Lab) · Xueyi Zou (Huawei Noah's Ark Lab) · Yulun Zhang (ETH Zurich) · Luc Van Gool (ETH Zurich)

The algebraic path problem for graph metrics
Enrique Fita Sanmartín (Heidelberg University) · Sebastian Damrich (Heidelberg University) · Fred Hamprecht (Heidelberg Collaboratory for Image Processing)

Robustness and Accuracy Could Be Reconcilable by (Proper) Definition
Tianyu Pang (Sea AI Lab) · Min Lin (Sea AI Lab) · Xiao Yang (Tsinghua University, Tsinghua University) · Jun Zhu (Tsinghua University) · Shuicheng Yan (Sea AI Labs)

Estimating Instance-dependent Label-noise Transition Matrix using a Deep Neural Network
Shuo Yang (University of Technology Sydney) · Erkun Yang (Xidian University) · Bo Han (HKBU / RIKEN) · Yang Liu (UC Santa Cruz) · Min Xu (Univeristy of Technology Sydney) · Gang Niu (RIKEN) · Tongliang Liu (The University of Sydney)

Learning inverse folding from millions of predicted structures
Chloe Hsu (University of California, Berkeley) · Robert Verkuil (Facebook AI Research) · Jason Liu (Facebook AI Reseach) · Zeming Lin (New York University) · Brian Hie (Stanford University) · Tom Sercu (Facebook AI Research) · Adam Lerer (Facebook AI Research) · Alexander Rives (FAIR)

FLPerf: A Comprehensive Benchmark for Federated Learning at Scale
Fan Lai (University of Michigan) · Yinwei Dai (University of Michigan) · Sanjay Singapuram (University of Michigan) · Jiachen Liu (University of Michigan) · Xiangfeng Zhu (University of Washington) · Harsha Madhyastha (University of Michigan) · Mosharaf Chowdhury (University of Michigan, Ann Arbor)

Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models
Fan Bao (Tsinghua University) · Chongxuan Li (Tsinghua University) · Jiacheng Sun (Huawei Noah's Ark Lab) · Jun Zhu (Tsinghua University) · Bo Zhang (Tsinghua University)

Loss Function Learning for Domain Generalization by Implicit Gradient
Boyan Gao (University of Edinburgh) · Henry Gouk (University of Edinburgh) · Yongxin Yang (University of Edinburgh ) · Timothy Hospedales (Samsung AI Centre / University of Edinburgh)

Scaling Structured Inference with Randomization
Yao Fu (University of Edinburgh) · John Cunningham (Columbia) · Mirella Lapata (University of Edinburgh)

Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition
Zheng Wang (University of Utah) · Shandian Zhe (University of Utah)

Variational Wasserstein gradient flow
Jiaojiao Fan (Georgia Institute of Technology) · Qinsheng Zhang (Georgia Institution of Technology) · Amirhossein Taghvaei (University of Washington Seattle) · Yongxin Chen (Georgia Institute of Technology)

Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search
Qi Wang (AMLab, University of Amsterdam) · Herke van Hoof (University of Amsterdam)

Neurocoder: General-Purpose Computation Using Stored Neural Programs
Hung Le (Deakin University) · Svetha Venkatesh (Deakin University)

Learning to Hash Robustly, Guaranteed
Alexandr Andoni () · Daniel Beaglehole (UCSD)

Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement Learning
Ruitu Xu (Yale University) · Yingjie Fei (Cornell University)

Learning to Solve PDE-constrained Inverse Problems with Graph Networks
QINGQING ZHAO (Stanford University) · David B. Lindell (Stanford University) · Gordon Wetzstein (Stanford University)

Distributionally-Aware Kernelized Bandit Problems for Risk Aversion
Sho Takemori (Fujitsu Limited)

Metric-Fair Classifier Derandomization
Jimmy Wu (N/A) · Yatong Chen (UC Santa Cruz) · Yang Liu (UC Santa Cruz)

CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
Yao Mu (The University of Hong Kong) · Shoufa Chen (The University of Hong Kong) · Mingyu Ding (The University of Hong Kong) · Jianyu Chen (Tsinghua University) · Runjian Chen (The University of Hong Kong) · Ping Luo (The University of Hong Kong)

Instance Dependent Regret Analysis of Kernelized Bandits
Shubhanshu Shekhar (University of California, San Diego) · Tara Javidi (University of California San Diego)

Federated Learning with Positive and Unlabeled Data
Xinyang Lin (Xi’an Jiaotong University) · Hanting Chen (Peking University) · Yixing Xu (Huawei Technologies) · Chao Xu (Peking University) · Xiaolin Gui (Xi'an jiaotong university) · Yiping Deng (Huawei) · Yunhe Wang (Noah's Ark Lab, Huawei Technologies.)

Searching for BurgerFormer with Micro-Meso-Macro Space Design
Longxing Yang (Institute of Computing Technology, Chinese Academy of Sciences) · Yu Hu (Institute of Computing Technology, Chinese Academy of Sciences) · Shun Lu (Institute of Computing Technology, Chinese Academy of Sciences) · Zihao Sun (Institute of Computing Technology, Chinese Academy of Sciences) · Jilin Mei (Institute of Computing Technology, Chinese Academy of Sciences) · Yinhe Han (Institute of Computing Technology Chinese Academy of Sciences) · Xiaowei Li (Institute Of Computing Technology Chinese Academy Of Sciences)

Translatotron 2: High-quality direct speech-to-speech translation with voice preservation
Ye Jia (Google) · Michelle Tadmor Ramanovich (Google) · Tal Remez (Google) · Roi Pomerantz (Google)

Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning
Jiahui Li (Zhejiang University) · Kun Kuang (Zhejiang University) · Baoxiang Wang (The Chinese University of Hong Kong, Shenzhen) · Furui Liu (Huawei Noah's Ark Lab) · Long Chen (Columbia University) · Changjie Fan (NetEase Fuxi AI Lab) · Fei Wu (Zhejiang University) · Jun Xiao (Zhejiang University)

GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks
Yixuan He (University of Oxford) · Quan Gan (Amazon) · David Wipf (Microsoft Research) · Gesine Reinert (University of Oxford) · Junchi Yan (Shanghai Jiao Tong University) · Mihai Cucuringu (University of Oxford and The Alan Turing Institute)

Reverse Engineering the Neural Tangent Kernel
James B Simon (UC Berkeley) · Sajant Anand (UC Berkeley) · Michael R DeWeese (UC Berkeley)

Interactively Learning Preference Constraints in Linear Bandits
David Lindner (ETH Zürich) · Sebastian Tschiatschek (University of Vienna) · Katja Hofmann (Microsoft) · Andreas Krause (ETH Zurich)

From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model
HeeSun Bae (KAIST) · Seungjae Shin (KAIST) · JoonHo Jang (KAIST) · Byeonghu Na (KAIST) · Kyungwoo Song (University of Seoul) · IL CHUL MOON (KAIST)

CITRIS: Causal Identifiability from Temporal Intervened Sequences
Phillip Lippe (University of Amsterdam) · Sara Magliacane (University of Amsterdam) · Sindy Löwe (University of Amsterdam) · Yuki Asano (University of Amsterdam) · Taco Cohen (Qualcomm) · Stratis Gavves (University of Amsterdam)

Path-aware and structure-preserving generation of synthetically accessible molecules
Juhwan Noh (Korea Advanced Institute of Science and Technology) · Dae-Woong Jeong (LG AI Research) · Kiyoung Kim (LG AI Research) · Sehui Han (LG AI Research) · Moontae Lee (LG AI Research) · Honglak Lee (LG AI Research / U. Michigan) · Yousung Jung (KAIST)

CerDEQ: Certifiable Deep Equilibrium Model
Mingjie Li (Peking University) · Yisen Wang (Peking University) · Zhouchen Lin (Peking University)

Exploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling
Yuanbang Liang (Cardiff University) · Jing Wu (Cardiff University) · Yu-Kun Lai (Cardiff University) · Yipeng Qin (Cardiff University)

Cooperative Online Learning in Stochastic and Adversarial MDPs
Tal Lancewicki (Tel-Aviv University) · Aviv Rosenberg (Tel Aviv University) · Yishay Mansour (Google and Tel Aviv University)

SAUTE RL: Toward Almost Surely Safe Reinforcement Learning Using State Augmentation
Aivar Sootla (Huawei R&D UK) · Alexander I Cowen-Rivers (Huawei R&D) · Taher Jafferjee (Huawei Technologies) · Ziyan Wang (Huawei Technologies Research & Development (UK) Ltd) · David Mguni (Noah's Ark Laboratory, Huawei) · Jun Wang (Huawei) · Haitham Bou Ammar (Huawei R&D UK and UCL)

PoF: Post-Training of Feature Extractor for Improving Generalization
Ikuro Sato (Tokyo Institute of Technology / Denso IT Laboratory) · Yamada Ryota (Tokyo Institute of Technology) · Masayuki Tanaka (Tokyo Institute of Technology) · Nakamasa Inoue (Tokyo Institute of Technology) · Rei Kawakami (Tokyo Institute of Technology / Denso IT Laboratory)

Selling Data To a Machine Learner: Pricing via Costly Signaling
Junjie Chen (City University of Hong Kong) · Minming Li (City University of Hong Kong) · Haifeng Xu (University of Virginia)

NOMU: Neural Optimization-based Model Uncertainty
Jakob Heiss (ETH Zürich) · Jakob Weissteiner (University of Zurich) · Hanna Wutte (ETH Zurich) · Sven Seuken (University of Zurich) · Josef Teichmann (ETH Zurich)

Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters
Luc Brogat-Motte (Télécom Paris) · Rémi Flamary (École Polytechnique) · Celine Brouard (INRAE) · Juho Rousu (Aalto University) · Florence d'Alché-Buc (Télécom Paris, Institut Polytechnique de Paris)

Thompson Sampling for (Combinatorial) Pure Exploration
Siwei Wang (Tsinghua University) · Jun Zhu (Tsinghua University)

Differentially Private Approximate Quantiles
Shachar Schnapp (Ben-Gurion University of the Negev) · Haim Kaplan (TAU, GOOGLE) · Uri Stemmer (Tel Aviv University and Google Research)

FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
Tian Zhou (Alibaba DAMO Academy) · Ziqing MA (Alibaba) · Qingsong Wen (Alibaba Group U.S.) · Xue Wang (Alibaba DAMO Academy) · Liang Sun (Alibaba Group) · rong jin (alibaba group)

Curriculum Reinforcement Learning via Constrained Optimal Transport
Pascal Klink (TU Darmstadt) · Haoyi Yang (TU Darmstadt) · Carlo D'Eramo (TU Darmstadt) · Jan Peters (TU Darmstadt) · Joni Pajarinen (Aalto University)

Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control
Liang Zhang (School of Life Sciences, Lanzhou University) · Qiang Wu (University of Electronic Science and Technology of China) · Jun Shen (University of Wollongong) · Linyuan Lü (University of Electronic Science and Technology of China) · Bo Du (University of Wollongong) · Jianqing Wu (Jiangxi University of Science and Technology)

NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework
Xingcheng Yao (Tsinghua University) · Yanan Zheng (Tsinghua University) · Xiaocong Yang (Tsinghua University) · Zhilin Yang (Recurrent AI)

Burst-dependent plasticity and dendritic amplification support target-based learning and hierarchical imitation learning
Cristiano Capone (INFN, Sezione di Roma) · Cosimo Lupo (INFN) · Paolo Muratore (SISSA, Trieste) · Pier Stanislao Paolucci (INFN Sezione di Roma)

Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection
Wenchao Chen (Xi'dian University) · Long Tian (Xidian University) · Bo Chen (School of Electronic Engineering, Xidian University) · Liang Dai (Institute of Information Engineering, Chinese Academy of Sciences) · Zhibin Duan (Xidian University) · Mingyuan Zhou (University of Texas at Austin)

Deep symbolic regression for recurrence prediction
Stéphane d'Ascoli (ENS / FAIR, Paris) · Pierre-Alexandre Kamienny (Facebook) · Guillaume Lample (Facebook AI Research) · Francois Charton (FAIR)

Simple and near-optimal algorithms for hidden stratification and multi-group learning
Christopher Tosh (Memorial Sloan Kettering) · Daniel Hsu (Columbia University)

Approximate Bayesian Computation with Domain Expert in the Loop
Ayush Bharti (Aalto University) · Louis Filstroff (Aalto University) · Samuel Kaski (Aalto University and University of Manchester)

Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification
Leo Schwinn (Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)) · Leon Bungert (University of Bonn) · An Nguyen (Friedrich-Alexander-Universität Erlangen-Nürnberg) · René Raab (Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)) · Falk Pulsmeyer (Friedrich-Alexander University Erlangen-Nürnberg) · Doina Precup (McGill University / DeepMind) · Bjoern Eskofier (Friedrich-Alexander-Universität Erlangen-Nürnberg) · Dario Zanca (Friedrich-Alexander-Universität Erlangen-Nürnberg)

Framework for Evaluating Faithfulness of Local Explanations
Sanjoy Dasgupta (UC San Diego) · Nave Frost (Tel-Aviv University) · Michal Moshkovitz (TAU)

Distinguishing rule- and exemplar-based generalization in learning systems
Ishita Dasgupta (DeepMind) · Erin Grant (UC Berkeley) · Thomas Griffiths (Princeton University)

Continuous Control with Action Quantization from Demonstrations
Robert Dadashi (Google Research) · Léonard Hussenot (Google Research, Brain Team) · Damien Vincent (Google Brain) · Sertan Girgin (Google Brain) · Anton Raichuk (Google) · Matthieu Geist (Google) · Olivier Pietquin (GOOGLE BRAIN)

Winning the Lottery Ahead of Time: Efficient Early Network Pruning
John Rachwan (Technical University of Munich) · Daniel Zügner (Technical University of Munich) · Bertrand Charpentier (Technical University of Munich) · Simon Geisler (Technical University of Munich) · Morgane Ayle (Technical University of Munich) · Stephan Günnemann (Technical University of Munich)

The Infinite Contextual Graph Markov Model
Daniele Castellana (Università di Pisa - Dipartimento di Informatica Largo B. Pontecorvo 3 56127; VAT: IT00286820501) · Federico Errica (NEC Laboratories Europe GmbH) · Davide Bacciu (University of Pisa) · Alessio Micheli (Universita di Pisa)

Constrained Variational Policy Optimization for Safe Reinforcement Learning
Zuxin Liu (Carnegie Mellon University) · Zhepeng Cen (Carnegie Mellon University) · Wei Liu (Nuro Inc.) · Vladislav Isenbaev (Nuro Inc.) · Steven Wu (Carnegie Mellon University) · Bo Li (UIUC) · Ding Zhao (Carnegie Mellon University)

Distribution Regression with Sliced Wasserstein Kernels
Dimitri Marie Meunier (UCL) · Carlo Ciliberto (University College London) · Massimiliano Pontil (Istituto Italiano di Tecnologia and University College London)

Generative Trees: Adversarial and Copycat
Richard Nock (Google Research) · Mathieu Guillame-Bert (Google)

Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering
Ekdeep Singh Lubana (University of Michigan) · Chi Ian Tang (University of Cambridge) · Fahim Kawsar (Nokia Bell Labs) · Robert Dick (University of Michigan) · Akhil Mathur (Bell Labs)

Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums
Sadegh Farhadkhani (EPFL) · Rachid Guerraoui (EPFL) · Nirupam Gupta (EPFL) · Rafael Pinot (EPFL - Ecocloud) · John Stephan (EPFL)

Label-Free Explainability for Unsupervised Models
Jonathan Crabbé (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

Learning Mixtures of Linear Dynamical Systems
Yanxi Chen (Princeton University) · H. Vincent Poor (Princeton University)

Correlation Clustering via Strong Triadic Closure Labeling: Fast Approximation Algorithms and Practical Lower Bounds
Nate Veldt (Texas A&M University)

Online Learning with Knapsacks: the Best of Both Worlds
Matteo Castiglioni (Politecnico di Milano) · Andrea Celli (Bocconi University) · Christian Kroer (Columbia University)

Nonparametric Embeddings of Sparse High-Order Interaction Events
Zheng Wang (University of Utah) · Yiming Xu (Univeristy of Utah) · Conor Tillinghast (Recursion) · Shibo Li (University of Utah) · Akil Narayan (University of Utah) · Shandian Zhe (University of Utah)

Data Scaling Laws in NMT: The Effect of Noise and Architecture
Yamini Bansal (Harvard University) · Behrooz Ghorbani (Google Research) · Ankush Garg (Google) · Biao Zhang (University of Edinburgh) · Colin Cherry (Google) · Behnam Neyshabur (Google) · Orhan Firat (Google)

Universality of Winning Tickets: A Renormalization Group Perspective
William T. Redman (UCSB) · Tianlong Chen (University of Texas at Austin) · Zhangyang “Atlas” Wang (University of Texas at Austin) · Akshunna S. Dogra (Imperial College London)

Accurate Quantization of Measures via Interacting Particle-based Optimization
Anna Korba (CREST/ENSAE, IP Paris) · Dejan Slepcev (Carnegie Mellon University) · Lantian Xu (Carnegie Mellon University)

Communicating via Maximum Entropy Reinforcement Learning
Samuel Sokota (Carnegie Mellon University) · Christian Schroeder (University of Oxford) · Maximilian Igl (University of Oxford) · Luisa Zintgraf (University of Oxford) · Phil Torr (Oxford) · Martin Strohmeier (armasuisse Science + Technology) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI) · Shimon Whiteson (University of Oxford) · Jakob Foerster (Oxford university)

Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback
Tianyi Lin (University of California, Berkeley) · Aldo Pacchiano (Microsoft Research) · Yaodong Yu (University of California, Berkeley) · Michael Jordan (UC Berkeley)

DNS: Determinantal Point Process Based Neural Network Sampler\\ for Ensemble Reinforcement Learning
Hassam Sheikh (Intel Labs) · Kizza Nandyose Frisbee (Intel Corporation) · mariano phielipp (Intel AI Labs)

Rethinking Graph Neural Networks for Anomaly Detection
Jianheng Tang (Hong Kong University of Science and Technology) · Jiajin Li (Stanford University ) · Ziqi Gao (Hong Kong University of Science and Technology) · Jia Li (Hong Kong University of Science and Technology)

Federated Minimax Optimization: Improved Convergence Analyses and Algorithms
PRANAY SHARMA (CARNEGIE MELLON UNIVERSITY) · Rohan Panda (Carnegie Mellon University) · Gauri Joshi (Carnegie Mellon University) · Pramod K Varshney (Syracuse University)

Debiaser Beware: Pitfalls of Centering Regularized Transport Maps
Aram-Alexandre Pooladian (New York University) · Jonathan Niles-Weed (NYU) · Marco Cuturi (ENSAE/CREST)

Federated Reinforcement Learning: Communication-Efficient Algorithms and Convergence Analysis
sajad khodadadian (georgia institute of technology) · PRANAY SHARMA (CARNEGIE MELLON UNIVERSITY) · Gauri Joshi (Carnegie Mellon University) · Siva Maguluri (Georgia Tech)

Task-aware Privacy Preservation for Multi-dimensional Data
Jiangnan Cheng (Cornell University) · Ao Tang (Cornell University) · Sandeep Chinchali (The University of Texas at Austin)

Set Based Stochastic Subsampling
Bruno Andreis (KAIST) · Seanie Lee (KAIST) · A. Tuan Nguyen (University of Oxford) · Juho Lee (KAIST, AITRICS) · Eunho Yang (KAIST) · Sung Ju Hwang (KAIST, AITRICS)

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Junlin Wu (Washington University in St. Louis) · Yevgeniy Vorobeychik (Washington University in St. Louis)

Towards understanding how momentum improves generalization in deep learning
Samy Jelassi (Princeton University) · Yuanzhi Li (CMU)

Partial Label Learning via Label Influence Function
Xiuwen Gong (The University of Sydney) · Dong Yuan (The University of Sydney) · Wei Bao (The University of Sydney)

Proximal and Federated Random Reshuffling
Konstantin Mishchenko (CNRS) · Ahmed Khaled (Princeton University) · Peter Richtarik (KAUST)

Co-training Improves Prompt-based Learning for Large Language Models
Hunter Lang (MIT) · Monica Agrawal (Massachusetts Institute of Technology) · Yoon Kim (Harvard University) · David Sontag (Massachusetts Institute of Technology)

Adaptive Random Walk Gradient Descent for Decentralized Optimization
Tao Sun (national university of defense technology) · Dongsheng Li (School of Computer Science, National University of Defense Technology) · Bao Wang (University of Utah)

The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces
Chi Jin (Princeton University) · Qinghua Liu (Princeton University) · Tiancheng Yu (MIT)

Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots
Yuanyuan Liu (Xidian University) · Fanhua Shang (School of Artificial Intelligence, Xidian University) · Weixin An (xidian university) · Hongying Liu (Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, China) · Zhouchen Lin (Peking University)

Dynamic Topic Models for Temporal Document Networks
Delvin Zhang (Singapore Management University) · Hady Lauw (Singapore Management University)

Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
Ling Pan (Tsinghua University) · Longbo Huang (Tsinghua University) · Tengyu Ma (Stanford) · Huazhe Xu (Stanford University)

Latent Diffusion Energy-Based Model for Interpretable Text Modelling
Peiyu Yu (University of California, Los Angeles) · Sirui Xie (UCLA) · Xiaojian Ma (Tsinghua University) · Baoxiong Jia (UCLA) · Bo Pang (University of California Los Angeles) · Ruiqi Gao (UCLA) · Yixin Zhu (Peking University) · Song-Chun Zhu (UCLA) · Ying Nian Wu (UCLA)

One-Pass algorithms for MAP Inference of Nonsymmetric Determinantal Point Processes
Aravind Reddy (Northwestern University) · Ryan A. Rossi (Adobe Research) · Zhao Song (Adobe Research) · Anup Rao (Adobe Research) · Tung Mai (Adobe Research) · Nedim Lipka (Adobe Research) · Gang Wu (Adobe Research) · Eunyee Koh (Adobe) · Nesreen K Ahmed (Intel AI Research)

Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
Dongjun Kim (KAIST) · Seungjae Shin (KAIST) · Kyungwoo Song (University of Seoul) · Wanmo Kang (KAIST) · IL CHUL MOON (KAIST)

Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
Haoxiang Wang (University of Illinois Urbana-Champaign) · Bo Li (UIUC) · Han Zhao (University of Illinois at Urbana-Champaign)

Provable Domain Generalization via Invariant-Feature Subspace Recovery
Haoxiang Wang (University of Illinois Urbana-Champaign) · Haozhe Si (University of Illinois Urbana Champaign) · Bo Li (UIUC) · Han Zhao (University of Illinois at Urbana-Champaign)

Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning
Chang Liu (Shanghai Jiao Tong University) · Chenfei Lou (Shanghai Jiao Tong University) · Runzhong Wang (Shanghai Jiao Tong University) · Alan Yuhan Xi (university of wisconsin madison) · Li Shen (JD Explore Academy) · Junchi Yan (Shanghai Jiao Tong University)

Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback
Fang Kong (Shanghai Jiao Tong University) · Yichi Zhou (Microsoft Research) · Shuai Li (Shanghai Jiao Tong University)

Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms
Jeongyeol Kwon (The University of Texas at Austin) · Yonathan Efroni (Microsoft Research, New York) · Constantine Caramanis (University of Texas) · Shie Mannor (Technion)

Estimation of Linear Non-Gaussian Latent Hierarchical Structure
Feng Xie (Peking University) · Biwei Huang (Carnegie Mellon University) · Zhengming Chen (Guangdong University of Technology) · Yangbo He (Peking University) · zhi geng (Peking University) · Kun Zhang (Carnegie Mellon University)

Rotting infinitely many-armed bandits
Jung-hun Kim (KAIST) · Milan Vojnovic (London School of Economics) · Se-Young Yun (KAIST)

Gradient-Free Method for Heavily Constrained Nonconvex Optimization
Wanli Shi (Nanjing University of Information Science & Technology) · Bin Gu (Nanjing University of Information Science & Technology) · Hongchang Gao (University of Pittsburgh)

On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features
Jinxin Zhou (University of Denver) · Xiao Li (University of Michigan) · Tianyu Ding (Microsoft) · Chong You (Google) · Qing Qu (University of Michigan) · Zhihui Zhu (University of Denver)

Multi-slots Online Matching with High Entropy
XINGYU LU (Ant Group) · Qintong Wu (Ant Group) · WENLIANG ZHONG (Ant Group)

Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features
Zhaowei Zhu (University of California, Santa Cruz) · Jialu Wang (University of California, Santa Cruz) · Yang Liu (UC Santa Cruz)

What Dense Graph Do You Need for Self-Attention?
Yuxin Wang (Fudan University) · Chu-Tak Lee (Fudan University) · Qipeng Guo (Fudan University) · Zhangyue Yin (Fudan University) · yunhua zhou (fudan university) · Xipeng Qiu (Fudan University) · Xuanjing Huang (Fudan University)

Interventional Contrastive Learning with Meta Semantic Regularizer
Wenwen Qiang (Institute of software Chinese academy of sciences) · Jiangmeng Li (Institute of Software Chinese Academy of Sciences) · Changwen Zheng (Institute of Software, Chinese Academy of Sciences) · Bing Su (Institute of Software, Chinese Academy of Sciences) · Hui Xiong (Baidu/Rutgers University)

Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense
Bao Gia Doan (University of Adelaide) · Ehsan Abbasnejad (University of Adelaide) · Javen Qinfeng Shi (University of Adelaide) · Damith Ranashinghe (The University of Adelaide)

Generalizing Gaussian Smoothing for Random Search
Katelyn Gao (Intel Labs) · Ozan Sener (Intel Labs)

Thompson Sampling for Robust Transfer in Multi-Task Bandits
Zhi Wang (University of California, San Diego) · Chicheng Zhang (University of Arizona) · Kamalika Chaudhuri (UCSD and Facebook AI Research)

Feature Learning and Signal Propagation in Deep Neural Networks
Yizhang Lou (University of Oxford) · Chris Mingard (University of Oxford) · Soufiane Hayou (National University of Singapore)

Understanding Robust Generalization in Learning Regular Languages
Soham Dan (University of Pennsylvania) · Osbert Bastani (University of Pennsylvania) · Dan Roth (University of Pennsylvania and AWS AI Labs)

Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming
Chuan Wen (Tsinghua University) · Jianing Qian (University of Pennsylvania) · Jierui Lin (UT Austin) · Jiaye Teng (Tsinghua University) · Dinesh Jayaraman (University of Pennsylvania) · Yang Gao (Tsinghua University)

ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder
Sangwon Kim (Keimyung University) · Jaeyeal Nam (Keimyung University) · Byoung Chul Ko (Keimyung University)

Instrumental Variable Regression with Confounder Balancing
Anpeng Wu (Zhejiang University) · Kun Kuang (Zhejiang University) · Bo Li (Tsinghua University) · Fei Wu (Zhejiang University, China)

Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training
Risheng Liu (Dalian University of Technology) · Xuan Liu (Dalian University of Technology) · Shangzhi Zeng (University of Victoria) · Jin Zhang (Southern University of Science and Technology) · Yixuan ZHANG (Southern University of Science and Technology)

A New Perspective on the Effects of Spectrum in Graph Neural Networks
mingqi yang (Dalian University of Technology) · Yanming Shen (Dalian University of Technology) · Rui Li (Dalian University of Technology) · Heng Qi (Dalian University of Technology) · Qiang Zhang (Dalian University of Technology) · Baocai Yin (Dalian University of Technology)

A Context-Integrated Transformer-Based Neural Network for Auction Design
Zhijian Duan (Peking University) · Jingwu Tang (Peking University) · Yutong Yin (Peking University) · Zhe Feng (Google Inc.) · Xiang Yan (Shanghai Jiao Tong University) · Manzil Zaheer (Google Research) · Xiaotie Deng (Peking University)

Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
Yan Zeng (ByteDance AI Lab) · Xinsong Zhang (Bytedance AI Lab) · Hang Li (Bytedance Technology)

Learning Domain Adaptive Object Detection with Probabilistic Teacher
Meilin Chen (Zhejiang University) · Weijie Chen (Zhejiang University) · Shicai Yang (Hikvision Research Institute) · Jie Song (Zhejiang University) · Xinchao Wang (National University of Singapore) · Lei Zhang (Chongqing University) · Yunfeng Yan (Zhejiang University) · Donglian Qi (Zhejiang University) · Yueting Zhuang (Zhejiang University) · Di Xie (Hikvision Research Institute) · Shiliang Pu (Hikvision Research Institute)

The Complexity of k-Means Clustering when Little is Known
Robert Ganian (TU Wien) · Thekla Hamm (TU Wien) · Viktoriia Korchemna (TU Wien) · Karolina Okrasa (University of Warsaw) · Kirill Simonov (University of Bergen)

Dataset Condensation with Contrastive Signals
Saehyung Lee (Seoul National University) · SANGHYUK CHUN (Naver corp.) · Sangwon Jung (Sungkwunkwan university) · Sangdoo Yun ( Clova AI Research, NAVER Corp.) · Sungroh Yoon (Seoul National University)

C*-algebra net: a new approach generalizing neural network parameters to C*-algebra
Yuka Hashimoto (NTT) · Zhao Wang (NTT) · Tomoko Matsui (Institute of Statistical Mathematics)

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets
Guy Hacohen (Hebrew University of Jerusalem) · Avihu Dekel (Hebrew University) · Daphna Weinshall (Hebrew University of Jerusalem, Israel)

FedNL: Making Newton-Type Methods Applicable to Federated Learning
Mher Safaryan (KAUST) · Rustem Islamov (MIPT) · Xun Qian (KAUST) · Peter Richtarik (KAUST)

Tell me why! Explanations support learning relational and causal structure
Andrew Lampinen (DeepMind) · Nicholas Roy (DeepMind) · Ishita Dasgupta (DeepMind) · Stephanie Chan (DeepMind) · Allison Tam (DeepMind) · James McClelland (Stanford University and Deepmind) · Chen Yan () · Adam Santoro (DeepMind) · Neil Rabinowitz (DeepMind) · Jane Wang (DeepMind) · Feilx Hill (Deepmind)

A Natural Actor-Critic Framework for Zero-Sum Markov Games
Ahmet Alacaoglu (University of Wisconsin-Madison) · Luca Viano (EPFL) · Niao He (ETH Zurich) · Volkan Cevher (EPFL)

Injecting Logical Constraints into Neural Networks via Straight-Through Estimators
Zhun Yang (Arizona State University) · Joohyung Lee (Samsung Research / Arizona State university) · Chiyoun Park (Samsung Research)

Bayesian Continuous-Time Tucker Decomposition
Shikai Fang (University of Utah) · Akil Narayan (University of Utah) · Robert Kirby (University of Utah) · Shandian Zhe (University of Utah)

Private Streaming SCO in $\ell_p$ geometry with Applications in High Dimensional Online Decision Making
Yuxuan Han (HKUST) · Zhicong Liang (Hong Kong University of Science and Technology) · Zhipeng Liang (Hong Kong University of Science and Technology) · Yang Wang (HKUST) · Yuan Yao (HongKong University of Science and Technology and Peking University) · Jiheng Zhang (HKUST)

XAI for Transformers: Better Explanations through Conservative Propagation
Ameen Ali (Tel Aviv University, Israel) · Thomas Schnake (TU Berlin) · Oliver Eberle (TU Berlin) · Grégoire Montavon (Technische Universität Berlin) · Klaus-robert Mueller (Technische Universität Berlin) · Lior Wolf (Facebook AI Research and Tel Aviv University)

Secure Distributed Training at Scale
Eduard Gorbunov (Moscow Institute of Physics and Technology) · Alexander Borzunov (HSE University, Yandex) · Michael Diskin (Yandex) · Max Ryabinin (Yandex/HSE University)

Implicit Bias of Linear Equivariant Networks
Hannah Lawrence (MIT) · Bobak T Kiani (MIT) · Kristian Georgiev (MIT) · Andrew Dienes (Massachusetts Institute of Technology)

Role-based Multiplex Network Embedding
Hegui Zhang (Southwestern University of Finance and Economics) · Gang Kou (Southwestern University of Finance and Economics)

Structure preserving neural networks: A case study in the entropy closure of the Boltzmann equation
Steffen Schotthöfer (Karlsruhe Institute of Technology (KIT)) · Tianbai Xiao (Karlsruhe Institute of Technology (KIT)) · Martin Frank (Karlsruhe Institute of Technology (KIT)) · Cory Hauck (Oak Ridge National Lab)

Adapting to Mixing Time in Stochastic Optimization with Markovian Data
Ron Dorfman (Technion) · Kfir Levy (Technion)

Deep and Flexible Graph Neural Architecture Search
Wentao Zhang (Peking University) · Yu Shen (Peking University) · Zheyu Lin (Peking University) · Yang Li (Peking University) · Zhi Yang (Peking University) · Bin Cui (Peking University)

Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes
Tim Tsz-Kit Lau (Northwestern University) · Han Liu (Northwestern)

Interactive Inverse Reinforcement Learning for Cooperative Games
Thomas Kleine Büning (University of Oslo) · Anne-Marie George (University of Oslo) · Christos Dimitrakakis (Chalmers / Harvard / Lille / Oslo)

A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources
Xiaoqing (Ellen) Tan (University of Pittsburgh) · Chung-Chou H. Chang (University of Pittsburgh) · Ling Zhou (Southwestern University of Finance and Economics) · Lu Tang (University of Pittsburgh)

Algorithms for the Communication of Samples
Lucas Theis (Google) · Noureldin Yosri Yehia Ahmed (Google)

Interactive Correlation Clustering with Existential Cluster Constraints
Rico Angell (University of Massachusetts Amherst) · Nicholas Monath (Google Research) · Nishant Yadav (University of Massachusetts Amherst) · Andrew McCallum (UMass Amherst)

Discrete Tree Flows via Tree-Structured Permutations
Mai Elkady (Purdue University) · Jim Lim (Purdue University) · David Inouye (Purdue University)

Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory
Ruiqi Zhang (Peking University) · Xuezhou Zhang (Princeton) · Chengzhuo Ni (Princeton University) · Mengdi Wang (Princeton University)

Supervised Learning with General Risk Functionals
Liu Leqi (Carnegie Mellon University) · Audrey Huang (University of Illinois Urbana-Champaign) · Zachary Lipton (Carnegie Mellon University) · Kamyar Azizzadenesheli (Purdue University)

Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups
David Knigge (University of Amsterdam) · David Romero (Vrije Universiteit Amsterdam) · Erik Bekkers (University of Amsterdam)

More Efficient Sampling for Tensor Decomposition with Worst-Case Guarantees
Osman Asif Malik (Lawrence Berkeley National Laboratory)

Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function
Qixin Zhang (City University of Hong Kong) · Zengde Deng (Cainiao Network) · Zaiyi Chen (University of Science and Technology of China) · Haoyuan Hu (Artificial Intelligence Department, Zhejiang Cainiao Supply Chain Management Co.) · Yu Yang (City University of Hong Kong)

Robustness in Multi-Objective Submodular Optimization: a Quantile Approach
Cedric Malherbe (Huawei Noah's Ark Lab) · Kevin Scaman (INRIA Paris)

Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots
Tanmay Shankar (Carnegie Mellon University) · Yixin Lin (Meta AI) · Aravind Rajeswaran (FAIR) · Vikash Kumar (Univ. Of Washington) · Stuart Anderson (Facebook AI Research) · Jean Oh (Carnegie Mellon University)

G$^2$CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters
Mingjie Li (Peking University) · Xiaojun Guo (Peking University) · Yifei Wang (Peking University) · Yisen Wang (Peking University) · Zhouchen Lin (Peking University)

Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning
Kaiwen Wang (Cornell University and Cornell Tech) · Xiaojie Mao (Tsinghua University) · Zhengyuan Zhou (Arena Technologies & NYU) · Nathan Kallus (Cornell University)

Zero-shot AutoML with Pretrained Models
Ekrem Öztürk (University of Freiburg) · Fabio Ferreira (University of Freiburg) · Hadi S Jomaa (Stiftung Universitat Hildesheim) · Lars Schmidt-Thieme (University of Hildesheim) · Josif Grabocka (Albert-Ludwigs-Universität Freiburg) · Frank Hutter (University of Freiburg and Bosch Center for Artificial Intelligence)

Fast Composite Optimization and Statistical Recovery in Federated Learning
Yajie Bao (Shanghai Jiao Tong University) · Michael Crawshaw (George Mason University) · Shan Luo (Shanghai Jiao Tong University) · Mingrui Liu (George Mason University)

Frustratingly Easy Transferability Estimation
Long-Kai Huang (Tencent AI Lab) · Ying WEI (City University of Hong Kong) · Yu Rong (Tencent AI Lab) · Qiang Yang (Hong Kong UST) · Junzhou Huang (University of Texas at Arlington / Tencent AI Lab)

Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous Features
Rahul Mazumder (Massachusetts Institute of Technology) · Xiang Meng (Massachusetts Institute of Technology) · Haoyue Wang (Massachusetts Institute of Technology)

A Functional Information Perspective on Model Interpretation
Itai Gat (Technion) · Nitay Calderon (Technion -- Israel Institute of Technology) · Roi Reichart (Technion) · Tamir Hazan (Technion)

Does the Data Induce Capacity Control in Deep Learning?
Rubing Yang (University of Pennsylvania) · Jialin Mao (University of Pennsylvania) · Pratik Chaudhari (University of Pennsylvania/Amazon Web Services)

Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks
Franco Pellegrini (École normale supérieure, Paris) · Giulio Biroli (ENS)

Linear Adversarial Concept Erasure
Shaul Ravfogel (Bar Ilan University) · Michael Twiton (Independent) · Yoav Goldberg () · Ryan Cotterell (ETH Zurich)

Inverse Contextual Bandits: Learning How Behavior Evolves over Time
Alihan Hüyük (University of Cambridge) · Daniel Jarrett (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

Why the Rich Get Richer? On the Balancedness of Random Partition Models
Changwoo Lee (Texas A&M University) · Huiyan Sang (Texas A&M University)

For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria
Scott Emmons (UC Berkeley) · Caspar Oesterheld (Carnegie Mellon University) · Andrew Critch (UC Berkeley) · Vincent Conitzer (Duke) · Stuart Russell (UC Berkeley)

Non-Vacuous Generalisation Bounds for Shallow Neural Networks
Feix Biggs (University College London) · Benjamin Guedj (Inria and University College London)

Prototype Based Classification from Hierarchy to Fairness
Mycal Tucker (Massachusetts Institute of Technology) · Julie Shah (MIT)

Differentially Private Coordinate Descent for Composite Empirical Risk Minimization
Paul Mangold (Inria) · Aurélien Bellet (INRIA) · Joseph Salmon (Université de Montpellier) · Marc Tommasi ()

Being Properly Improper
Tyler Sypherd (Arizona State University) · Richard Nock (Google Research) · Lalitha Sankar (Arizona State University)

Intriguing Properties of Input-Dependent Randomized Smoothing
Peter Súkeník (Institute of Science and Technology, Austria (ISTA)) · Aleksei Kuvshinov (Technical University of Munich) · Stephan Günnemann (Technical University of Munich)

Deep Reference Priors: What is the best way to pretrain a model?
Yansong Gao (University of Pennsylvania) · Rahul Ramesh (University of Pennsylvania) · Pratik Chaudhari (University of Pennsylvania/Amazon Web Services)

Fair Representation Learning through Implicit Path Alignment
Changjian Shui (Université Laval) · Qi CHEN (Laval University) · Jiaqi Li (University of Western Ontario) · Boyu Wang (University of Western Ontario) · Christian Gagne (Université Laval)

HyperImpute: Generalized Iterative Imputation with Automatic Model Selection
Bogdan Cebere (University of Cambridge) · Daniel Jarrett (University of Cambridge) · Tennison Liu (University of Cambridge) · Alicia Curth (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning
Shay Vargaftik (VMware) · Ran Ben Basat (UCL) · Amit Portnoy (Ben-Gurion University) · Gal Mendelson (Stanford) · Yaniv Ben Itzhak (VMware) · Michael Mitzenmacher (Harvard)

Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering
Peng Wang (University of Michigan) · Huikang Liu (Imperial College London) · Anthony Man-Cho So (The Chinese University of Hong Kong) · Laura Balzano (University of Michigan)

The power of first-order smooth optimization for black-box non-smooth problems
Alexander Gasnikov (Moscow Institute of Physics and Technology) · Anton Novitskii (MIPT) · Vasilii Novitskii (MIPT) · Farshed Abdukhakimov (MBZUAI) · Dmitry Kamzolov (Mohamed bin Zayed University of Artificial Intelligence) · Aleksandr Beznosikov (Moscow Institute of Physics and Technology (National Research University)) · Martin Takac (MBZUAI) · Pavel Dvurechenskii (Weierstrass Institute) · Bin Gu (Nanjing University of Information Science & Technology)

Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets
Lily Zhang (New York University) · Veronica Tozzo (Massachusets General Hospital Harvard Medical School) · John Higgins (Massachusets General Hospital - Harvard Medical School) · Rajesh Ranganath (New York University)

Imitation Learning by Estimating Expertise of Demonstrators
Mark Beliaev (University of California, Santa Barbara) · Andy Shih (Stanford University) · Stefano Ermon (Stanford University) · Dorsa Sadigh (Stanford University) · Ramtin Pedarsani (UC Santa Barbara)

Combining Diverse Feature Priors
Saachi Jain (Massachusetts Institute of Technology) · Dimitris Tsipras (Stanford University) · Aleksander Madry (MIT)

A Simple Unified Framework for High Dimensional Bandit Problems
Wenjie Li (Purdue University) · Adarsh Barik (Purdue University) · Jean Honorio (Purdue University)

Generalized Results for the Existence and Consistency of the MLE in the Bradley-Terry-Luce Model
Heejong Bong (Carnegie Mellon University) · Alessandro Rinaldo (Carnegie Mellon University)

Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Chris Dann (Google) · Yishay Mansour (Google) · Mehryar Mohri (Google Research and Courant Institute of Mathematical Sciences) · Ayush Sekhari (Cornell University) · Karthik Sridharan (Cornell University)

Coin Flipping Neural Networks
Yuval Sieradzki (Technion Israel Institute of Technology) · Nitzan Hodos (Technion - Israel Institute of Technology) · Gal Yehuda (Technion) · Assaf Schuster (Technion)

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Edresson Casanova (University of São Paulo) · Julian Weber (Coqui.ai) · Christopher Shulby (University of São Paulo) · Arnaldo Candido Junior (Federal University of Technology – Paraná) · Eren Gölge (Coqui) · Moacir Ponti (Universidade de São Paulo (ICMC-USP))

Sublinear-Time Clustering Oracle for Signed Graphs
Stefan Neumann (KTH Royal Institute of Technology) · Pan Peng (University of Science and Technology of China)

Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
xinwei zhang (University of Minnesota) · Xiangyi Chen (University of Minnesota) · Mingyi Hong (University of Minnesota) · Steven Wu (Carnegie Mellon University) · Jinfeng Yi (JD AI Research)

Matching Normalizing Flows and Probability Paths on Manifolds
Heli Ben-Hamu (Weizmann Institute of Science) · samuel cohen (University College London) · Joey Bose (McGill/Mila) · Brandon Amos (Meta AI (FAIR)) · Maximilian Nickel (Facebook AI Research) · Aditya Grover (UCLA) · Ricky T. Q. Chen (Facebook AI Research) · Yaron Lipman (Facebook AI Research)

Reinforcement Learning with Action-Free Pre-Training from Videos
Younggyo Seo (KAIST) · Kimin Lee (Google) · Stephen James (UC Berkeley) · Pieter Abbeel (UC Berkeley & Covariant)

Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures
Nelson Vadori (J.P. Morgan AI Research) · Rahul Savani (Univ. of Liverpool) · Thomas Spooner (-) · Sumitra Ganesh (JPMorgan)

Out-of-Distribution Detection with Posterior Sampling
Yifei Ming (University of Wisconsin-Madison) · Ying Fan (University of Wisconsin-Madison) · Yixuan Li (University of Wisconsin-Madison)

Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach
Xuezhou Zhang (Princeton) · Yuda Song (Carnegie Mellon University) · Masatoshi Uehara (Cornell University) · Mengdi Wang (Princeton University) · Alekh Agarwal (Microsoft Research) · Wen Sun (Cornell University)

On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation
Xiaohong Chen (Yale University) · Zhengling Qi (The George Washington University)

Towards Adaptive Model-Based Reinforcement Learning
Yi Wan (University of Alberta) · Harm van Seijen (Microsoft Research) · Ida Momennejad (Microsoft Research) · Sarath Chandar (Polytechnique Montreal) · Janarthanan Rajendran (Mila, University of Montreal) · Ali Rahimi-Kalahroudi (MILA - Université de Montréal)

Popular decision tree algorithms are provably noise tolerant
Guy Blanc (Stanford University) · Jane Lange (MIT) · Ali Malik (Stanford Universtiy) · Li-Yang Tan (Stanford University)

Causal Conceptions of Fairness and their Consequences
Hamed Nilforoshan (Stanford) · Johann Gaebler (Stanford University) · Ravi Shroff (NYU) · Sharad Goel (Harvard University)

To Smooth or Not? When Label Smoothing Meets Noisy Labels
Jiaheng Wei (University of California, Santa Cruz) · Hangyu Liu (Brown University) · Tongliang Liu (The University of Sydney) · Gang Niu (RIKEN) · Masashi Sugiyama (RIKEN / The University of Tokyo) · Yang Liu (UC Santa Cruz)

Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error
Scott Fujimoto (McGill University) · David Meger (McGill University) · Doina Precup (McGill University / DeepMind) · Ofir Nachum (Google Brain) · Shixiang Gu (Google)

Modeling Strong and Human-Like Gameplay with KL-Regularized Search
Athul Paul Jacob (MIT) · David Wu (FAIR) · Gabriele Farina (Carnegie Mellon University) · Adam Lerer (Facebook AI Research) · Hengyuan Hu (Facebook AI Research) · Anton Bakhtin (Facebook AI Research) · Jacob Andreas (MIT) · Noam Brown (Facebook AI Research)

On the Difficulty of Defending Self-Supervised Learning against Model Extraction
Adam Dziedzic (The University of Toronto & Vector Institute) · Nikita Dhawan (University of Toronto and Vector Institute) · Muhammad Ahmad Kaleem (University of Toronto) · Jonas Guan (University of Toronto) · Nicolas Papernot (University of Toronto and Vector Institute)

Distributionally Robust $Q$-Learning
Zijian Liu (Boston University) · Zhengqing Zhou (Stanford University) · Perry Dong (University of California, Berkeley) · Jerry Bai (Horizon Robotics) · Jose Blanchet (Stanford University) · Wei Xu (Horizon Robotics) · Zhengyuan Zhou (Arena Technologies & NYU)

Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile
Dong Chen (Zhejiang University) · Lingfei Wu (JD.COM Silicon Valley Research Center) · Siliang Tang (Zhejiang University) · Xiao Yun (JD.com) · Bo Long (JD.com) · Yueting Zhuang (Zhejiang University)

Structure-preserving GANs
Jeremiah Birrell (University of Massachusetts Amherst) · Markos Katsoulakis (UMass Amherst) · Wei Zhu (University of Massachusetts Amherst) · Luc Rey-Bellet (UMass Amherst)

NysADMM: faster composite convex optimization via low-rank approximation
Shipu Zhao (Cornell University) · Zachary Frangella (Cornell University) · Madeleine Udell (Cornell University)

More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize
Alexander Wei (UC Berkeley) · Wei Hu (UC Berkeley / UMich) · Jacob Steinhardt (UC Berkeley)

Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games
Gabriele Farina (Carnegie Mellon University) · Chung-Wei Lee (University of Southern California) · Haipeng Luo (University of Southern California) · Christian Kroer (Columbia University)

LIMO: Latent Inceptionism for Targeted Molecule Generation
Peter Eckmann (University of California, San Diego) · Kunyang Sun (UCSD) · Bo Zhao (University of California, San Diego) · Mudong Feng (University of California, San Diego) · Michael Gilson (University of California, San Diego) · Rose Yu (University of California, San Diego)

Coordinated Double Machine Learning
Nitai Fingerhut (Technion) · Yaniv Romano (Technion---Israel Institute of Technology) · Matteo Sesia (University of Southern California)

Public Data-Assisted Mirror Descent for Private Model Training
Ehsan Amid (Google Brain) · Arun Ganesh (UC Berkeley) · Rajiv Mathews (Google) · Swaroop Ramaswamy (Google) · Shuang Song (Google) · Thomas Steinke (Google) · Thomas Steinke (Google) · Vinith Suriyakumar (Massachusetts Institute of Technology) · Om Thakkar (Google) · Abhradeep Guha Thakurta (Google)

Learning from Counterfactual Links for Link Prediction
Tong Zhao (Snap Inc.) · Gang Liu (University of Notre Dame) · Daheng Wang (University of Notre Dame) · Wenhao Yu (University of Notre Dame) · Meng Jiang (University of Notre Dame)

Generating 3D Molecules for Target Protein Binding
Meng Liu (Texas A&M University) · Youzhi Luo (Texas A&M University) · Kanji Uchino (FUJITSU Research OF AMERICA, INC.) · Koji Maruhashi (Fujitsu Research, Fujitsu Limited) · Shuiwang Ji (Texas A&M University)

A Temporal-Difference Approach to Policy Gradient Estimation
Samuele Tosatto (University of Alberta) · Andrew Patterson (University of Alberta) · Martha White (University of Alberta) · A. Mahmood ()

Convergence of Invariant Graph Networks
Chen Cai (University of California, San Diego) · Yusu Wang (UC San Diego)

Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization
Yihua Zhang (Michigan State University) · Guanhua Zhang (UC, Santa Barbara) · Prashant Khanduri (University Of Minnesota) · Mingyi Hong (University of Minnesota) · Shiyu Chang (UCSB) · Sijia Liu (Michigan State University)

Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptation
Justin Jude (University of Edinburgh) · Matthew G. Perich (Université de Montréal) · Lee Miller (Northwestern University) · Matthias Hennig (University of Edinburgh)

Sequential Covariate Shift Detection Using Classifier Two-Sample Tests
Sooyong Jang (University of Pennsylvania) · Sangdon Park (Georgia Institute of Technology) · Insup Lee (University of Pennsylvania) · Osbert Bastani (University of Pennsylvania)

Variational nearest neighbor Gaussian process
Luhuan Wu (Columbia University) · Geoff Pleiss (Columbia University) · John Cunningham (Columbia University)

RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression
Yu Gong (Simon Fraser University) · Greg Mori (Simon Fraser University / Borealis AI) · Frederick Tung (Borealis AI)

Power-law escape rate of SGD
Takashi Mori (Riken) · Liu Ziyin (University of Tokyo) · Kangqiao Liu (University of Tokyo) · Masahito Ueda (University of Tokyo)

Improving Mini-batch Optimal Transport via Partial Transportation
Khai Nguyen (University of Texas at Austin) · Dang Nguyen (VinAI) · The-Anh Vu-Le (VinAI) · Tung Pham (VINAI ARTIFICIAL INTELLIGENCE APPLICATION AND RESEARCH JOINT STOCK COMPANY) · Nhat Ho (University of Texas at Austin)

UNITE: Uncertainty Adjusted Pruning for Large Transformer Models
Qingru Zhang (Georgia Institute of Technology) · Simiao Zuo (Georgia Institute of Technology) · Chen Liang (Georgia Institute of Technology) · Alexander Bukharin (Georgia Institute of Technology) · Pengcheng He (Microsoft) · Weizhu Chen (Microsoft) · Tuo Zhao (Georgia Tech)

On Transportation of Mini-batches: A Hierarchical Approach
Khai Nguyen (University of Texas at Austin) · Dang Nguyen (VinAI) · Quoc Nguyen (VinAI) · Tung Pham (VINAI ARTIFICIAL INTELLIGENCE APPLICATION AND RESEARCH JOINT STOCK COMPANY) · Hung Bui (VinAI Research) · Dinh Phung (Monash University, Australia) · Trung Le (Monash University) · Nhat Ho (University of Texas at Austin)

Hessian-Free High-Resolution Nesterov Acceleration For Sampling
Ruilin Li (Georgia Institute of Technology) · Hongyuan Zha (Shenzhen Institute of Artificial Intelligence and Robotics for Society; The Chinese University of Hong Kong, Shenzhen) · Molei Tao (Georgia Institute of Technology)

Approximately Equivariant Networks for Imperfectly Symmetric Dynamics
Rui Wang (University of California, San Diego) · Robin Walters (Northeastern University) · Rose Yu (University of California, San Diego)

Contrastive Learning with Boosted Memorization
Zhihan Zhou (Cooperative Medianet Innovation Center, Shanghai Jiao Tong University) · Jiangchao Yao (Cooperative Medianet Innovation Center, Shang hai Jiao Tong University) · Yan-Feng Wang (Cooperative medianet innovation center of Shanghai Jiao Tong University) · Bo Han (HKBU / RIKEN) · Ya Zhang (Cooperative Medianet Innovation Center, Shang hai Jiao Tong University)

Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
Xiang Li (East China Normal University) · Renyu Zhu (East China Normal University) · Yao Cheng (East China Normal University) · Caihua Shan (Microsoft) · Siqiang Luo (Nanyang Technological University) · Dongsheng Li (Microsoft Research Asia) · Weining Qian (East China Normal University)

UAST: Uncertainty-Aware Siamese Tracking
Dawei Zhang (Zhejiang Normal University) · Yanwei Fu (Fudan university) · Zhonglong Zheng (Zhejiang Normal University)

Deep Hierarchy in Bandits
Joey Hong (Berkeley) · Sumeet Katariya (UW-Madison and Amazon) · Branislav Kveton (Google Research) · Manzil Zaheer (Google Research) · Mohammad Ghavamzadeh (Google Research)

NeuralEF: Deconstructing Kernels by Deep Neural Networks
Zhijie Deng (Tsinghua University) · Jiaxin Shi (Microsoft Research New England) · Jun Zhu (Tsinghua University)

Neural Implicit Dictionary Learning via Mixture-of-Expert Training
Peihao Wang (The University of Texas at Austin) · Zhiwen Fan (University of Texas at Austin) · Tianlong Chen (University of Texas at Austin) · Zhangyang “Atlas” Wang (University of Texas at Austin)

Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL
Siyi Hu (Monash University) · Chuanlong Xie (Beijing Normal University) · Xiaodan Liang (Sun Yat-sen University) · Xiaojun Chang (University of Technology Sydney)

Learning Stochastic Shortest Path with Linear Function Approximation
Yifei Min (Yale University) · Jiafan He (University of California, Los Angeles) · Tianhao Wang (Yale University) · Quanquan Gu (University of California, Los Angeles)

GALAXY: Graph-based Active Learning at the Extreme
Jifan Zhang (University of Wisconsin) · Julian Katz-Samuels (University of Wisconsin-Madison) · Robert Nowak (University of Wisconsion-Madison)

Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(\epsilon^{-7/4})$ Complexity
Huan Li (Nankai University) · Zhouchen Lin (Peking University)

A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games
Wei Xiong (The Hong Kong University of Science and Technology) · Han Zhong (Peking University) · Chengshuai Shi (University of Virginia) · Cong Shen (University of Virginia) · Tong Zhang (HKUST)

Fairness with Adaptive Weights
Junyi Chai (Purdue University) · Xiaoqian Wang (Purdue University)

An Improved Analysis of Algorithmic Robustness
Kenji Kawaguchi (National University of Singapore) · Kyle Luh (Harvard Unversity) · Jiaoyang Huang (IAS) · Zhun Deng (Harvard)

Non-Stationary Dueling Bandits
Aadirupa Saha (Microsoft Research) · Shubham Gupta (IBM Research)

Residual-based Sampling for Online Outlier Robust PCA
Tianhao Zhu (Stevens Institute of Technology) · Jie Shen (Stevens Institute of Technology)

MemSR: Training Memory-efficient Lightweight Model for Image Super-Resolution
Kailu Wu (Tsinghua University) · Chung-Kuei Lee (Huawei) · Kaisheng Ma (Tsinghua University )

Neural-Symbolic Models for Logical Queries on Knowledge Graphs
Zhaocheng Zhu (Mila - Quebec AI Institute) · Mikhail Galkin (Mila, McGill University) · Zuobai Zhang (Mila) · Jian Tang (HEC Montreal & MILA)

Streaming Inference for Infinite Feature Models
Rylan Schaeffer (Stanford University) · Yilun Du (MIT) · Gabrielle K Liu (Massachusetts Institute of Technology) · Ila R. Fiete (MIT)

Causal Inference Principles for Reasoning about Commonsense Causality
Jiayao Zhang (University of Pennsylvania) · Hongming ZHANG (Tencent AI Lab, Seattle) · Dan Roth (University of Pennsylvania and AWS AI Labs) · Weijie Su (University of Pennsylvania)

ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias
Yupu Lu (The University of Hong Kong) · Shijie Lin (The University of Hong Kong) · Guanqi Chen (The University of Hong Kong) · Jia Pan (The University of Hong Kong)

Bayesian Optimization under Stochastic Delayed Feedback
Arun Verma (National University of Singapore) · Zhongxiang Dai (National University of Singapore) · Bryan Kian Hsiang Low (National University of Singapore)

Robust Training of Deep Networks by Sparse Over-parameterization
Sheng Liu (NYU) · Zhihui Zhu (University of Denver) · Qing Qu (University of Michigan) · Chong You (Google)

Neuron Dependency Graphs: A Causal Abstraction of Neural Networks
Yaojie Hu (Iowa State University) · Jin Tian (Iowa State University)

Branching Reinforcement Learning
Yihan Du (IIIS, Tsinghua University) · Wei Chen (Microsoft)

Solving Stackelberg Prediction Game with Least Squares Loss Via Spherically Constrained Least Squares Reformulation
Jiali Wang (fudan university) · Wen Huang (Xiamen University) · Rujun Jiang (Fudan University) · Xudong Li (Fudan University) · Alex Wang (Carnegie Mellon University)

Topology-aware Generalization of Decentralized SGD
Tongtian Zhu (Zhejiang University) · Fengxiang He (JD.com Inc) · Lan Zhang (University of Science and Technology of China) · Zhengyang Niu (Wuhan University) · Mingli Song (Zhejiang University) · Dacheng Tao ()

Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits
Avishek Ghosh (University of California, San Diego) · Abishek Sankararaman (Amazon Web Services)

Uncertainty Modeling in Generative Compressed Sensing
Yilang Zhang (Fudan University) · Mengchu Xu (Fudan University) · Xiaojun Mao (Shanghai Jiao Tong University) · Jian Wang (Fudan University)

Detecting Corrupted Labels Without Training a Model to Predict
Zhaowei Zhu (University of California, Santa Cruz) · Zihao Dong (University of California, Santa Cruz) · Yang Liu (UC Santa Cruz)

Forgetting-free Continual Learning with Winning Subnetworks
Haeyong Kang (KAIST) · Rusty Mina (N/A) · Sultan Rizky Hikmawan Madjid (Korea Advanced Institute of Science and Technology) · Jaehong Yoon (KAIST) · Chang Yoo (KAIST) · Sung Ju Hwang (KAIST, AITRICS) · Mark Hasegawa-Johnson (University of Illinois)

Tight and Robust Private Mean Estimation with Few Users
Shyam Narayanan (Massachusetts Institute of Technology) · Vahab Mirrokni (Google Research) · Hossein Esfandiari (Google Research)

Permutation Search of Tensor Network Structures via Local Sampling
Chao Li (RIKEN Center for Advanced Intelligence Project) · Junhua Zeng (Guangdong University of Technology) · Zerui Tao (Tokyo University of Agriculture and Technology) · Qibin Zhao (RIKEN)

A Hierarchical Transitive-Aligned Graph Kernel for Un-attributed Graphs
Lu Bai (Beijing Normal University, Beijing, China. Central University of Finance and Economics, Beijing, China.) · Lixin Cui (Central University of Finance and Economics, China) · Edwin Hancock ("University of York, UK")

Composing Partial Differential Equations with Physics-Aware Neural Networks
Matthias Karlbauer (University of Tübingen) · Timothy Praditia (University of Stuttgart) · Sebastian Otte (University of Tübingen) · Sergey Oladyshkin (University of Stuttgart) · Wolfgang Nowak (University of Stuttgart) · Martin V Butz (University of Tübingen)

Optimal Clustering with Noisy Queries via Multi-Armed Bandit
Jinghui Xia (Fudan University) · Zengfeng Huang (Fudan University)

Offline RL Policies Should Be Trained to be Adaptive
Dibya Ghosh (Google) · Anurag Ajay (MIT) · Pulkit Agrawal (MIT) · Sergey Levine (UC Berkeley)

FriendlyCore: Practical Differentially Private Aggregation
Eliad Tsfadia (Tel Aviv University and Google Research) · Edith Cohen (Google Research and Tel Aviv University) · Haim Kaplan (TAU, GOOGLE) · Yishay Mansour (Google and Tel Aviv University) · Uri Stemmer (Tel Aviv University and Google Research)

Efficient Distributionally Robust Bayesian Optimization with Worst-case Sensitivity
Sebastian Tay (National University of Singapore) · Chuan Sheng Foo (Institute for Infocomm Research, A*STAR) · Urano Daisuke (Temasek Life Sciences Laboratory) · Richalynn Leong (Temasek Life Sciences Laboratory) · Bryan Kian Hsiang Low (National University of Singapore)

Understanding Gradient Descent on the Edge of Stability in Deep Learning
Sanjeev Arora (Princeton University) · Zhiyuan Li (Princeton University) · Abhishek Panigrahi (Princeton University)

Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs
Yikang Zhang (Huawei) · zhuo chen (HUAWEI) · Zhao Zhong (HUAWEI)

Centroid Approximation for Bootstrap: Improving Particle Quality at Inference
Mao Ye (UT Austin) · Qiang Liu (UT Austin)

Information-Intensive Dataset Condensation
Jang-Hyun Kim (Seoul National University) · Jinuk Kim (Seoul National University) · Seong Joon Oh (AI Lab, Naver) · Sangdoo Yun ( Clova AI Research, NAVER Corp.) · Hwanjun Song (NAVER AI Lab) · Joonhyun Jeong (Clova Image Vision, NAVER Corp.) · Jung-Woo Ha (Clova AI Research, NAVER Corp.) · Hyun Oh Song (Seoul National University)

Analyzing and Mitigating Interference in Neural Architecture Search
Jin Xu (Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University) · Xu Tan (Microsoft Research) · Kaitao Song (Microsoft Research Asia) · Renqian Luo (Microsoft Research Asia) · Yichong Leng (University of Science and Technology of China) · Tao Qin (Microsoft Research Asia) · Tie-Yan Liu (Microsoft Research Asia) · Jian Li (IIIS)

Re-evaluating Word Mover's Distance
Ryoma Sato (Kyoto University) · Makoto Yamada (RIKEN AIP / Kyoto University) · Hisashi Kashima (Kyoto University/RIKEN Center for AIP)

AGNAS: Attention-Guided Unifying Micro- and Macro-Architecture Search
Zihao Sun (Institute of Computing Technology, Chinese Academy of Sciences) · Yu Hu (Institute of Computing Technology, Chinese Academy of Sciences) · Shun Lu (Institute of Computing Technology, Chinese Academy of Sciences) · Longxing Yang (Institute of Computing Technology, Chinese Academy of Sciences) · Jilin Mei (Institute of Computing Technology, Chinese Academy of Sciences) · Yinhe Han (Institute of Computing Technology Chinese Academy of Sciences) · Xiaowei Li (Institute Of Computing Technology Chinese Academy Of Sciences)

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
Deokjae Lee (Seoul National University) · Seungyong Moon (Seoul National University) · Junhyeok Lee (Seoul National University) · Hyun Oh Song (Seoul National University)

On Numerical Integration in Neural Ordinary Differential Equations
Aiqing Zhu (Academy of Mathematics and Systems Science, Chinese Academy of Sciences) · Pengzhan Jin (Peking University) · Beibei Zhu (University of Science and Technology Beijing) · Yifa Tang (Academy of Mathematics and Systems Science, Chinese Academy of Sciences)

Learning Infinite-horizon Average-reward Markov Decision Process with Constraints
Liyu Chen (USC) · Rahul Jain (USC) · Haipeng Luo (University of Southern California)

Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP
Liyu Chen (USC) · Rahul Jain (USC) · Haipeng Luo (University of Southern California)

VLUE: A Multi-Task Multi-Dimension Benchmark for Evaluating Vision-Language Pre-training
Wangchunshu Zhou (Beihang Univerisity) · Yan Zeng (ByteDance AI Lab) · shizhe diao (HKUST) · Xinsong Zhang (Bytedance AI Lab)

Dimension-free Complexity Bounds for High-order Nonconvex Finite-sum Optimization
Dongruo Zhou (UCLA) · Quanquan Gu (University of California, Los Angeles)

Variational Feature Pyramid Networks
PANAGIOTIS DIMITRAKOPOULOS (University of Ioannina) · Giorgos Sfikas (University of Ioannina) · CHRISTOPHOROS NIKOU (University of Ioannina)

DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning
Robert Hönig (University of Cambridge) · Yiren Zhao (University of Cambridge) · Robert Mullins (University of Cambridge)

Near-Optimal Learning of Extensive-Form Games with Imperfect Information
Yu Bai (Salesforce Research) · Chi Jin (Princeton University) · Song Mei (UC Berkeley) · Tiancheng Yu (MIT)

Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
Zeke Xie (The University of Tokyo/RIKEN AIP) · Xinrui Wang (The University of Tokyo) · Huishuai Zhang (Microsoft) · Issei Sato (The University of Tokyo) · Masashi Sugiyama (RIKEN / The University of Tokyo)

Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images
Tom Ron (The Technion) · Tamir Hazan (Technion)

GACT: Activation Compressed Training for Generic Network Architectures
Xiaoxuan Liu (UC Berkeley) · Lianmin Zheng (UC Berkeley) · Dequan Wang (UC Berkeley) · Yukuo Cen (Tsinghua University) · Weize Chen (Tsinghua University) · Xu Han (Tsinghua University) · Jianfei Chen (Tsinghua University) · Zhiyuan Liu (Tsinghua University) · Jie Tang (Tsinghua University) · Joseph Gonzalez (UC Berkeley) · Michael Mahoney (UC Berkeley) · Alvin Cheung (University of California, Berkeley)

Improving language models by retrieving from trillions of tokens
Sebastian Borgeaud (DeepMind) · Arthur Mensch (Deepmind) · Jordan Hoffmann (DeepMind) · Trevor Cai (DeepMind) · Eliza Rutherford (DeepMind) · Katie Millican (DeepMind) · George van den Driessche (DeepMind) · Jean-Baptiste Lespiau (DeepMind) · Bogdan Damoc (DeepMind) · Aidan Clark (OpenAI) · Diego de Las Casas (DeepMind) · Aurelia Guy (Google Inc.) · Jacob Menick (DeepMind) · Roman Ring (DeepMind) · Tom Hennigan (DeepMind) · Saffron Huang (DeepMind) · Loren Maggiore (DeepMind) · Chris Jones (DeepMind) · Albin Cassirer (DeepMind) · Andy Brock (DeepMind) · Michela Paganini (DeepMind) · Geoffrey Irving (DeepMind) · Oriol Vinyals (Google DeepMind) · Simon Osindero (DeepMind) · Karen Simonyan (Inflection AI) · Jack Rae (DeepMind) · Erich Elsen (Google) · Laurent Sifre (DeepMind)

Revisiting the Effects of Stochasticity for Hamiltonian Samplers
Giulio Franzese (EURECOM) · Dimitrios Milios (EURECOM) · Maurizio Filippone (EURECOM) · Pietro Michiardi (EURECOM)

Rethinking Convergence in Deep Learning: Beyond Stationary Points
Jingzhao Zhang (Tsinghua University) · Haochuan Li (MIT) · Suvrit Sra (MIT) · Ali Jadbabaie (Massachusetts Institute of Technology)

Fictitious Play and Best-Response Dynamics in Identical Interest and Zero-Sum Stochastic Games
Lucas Baudin (Université Paris-Dauphine) · Rida Laraki (Université Paris-Dauphine)

Learning of Cluster-based Feature Importance for Electronic Health Record Time-series
Henrique Aguiar (University of Oxford) · Mauro Santos (University of Oxford) · Peter Watkinson (Oxford University Hospitals NHS Foundation Trust) · Tingting Zhu (University of Oxford)

Adaptive Data Analysis with Correlated Observations
Menachem Sadigurschi (Ben Gurion University) · Uri Stemmer (Tel Aviv University and Google Research) · Aryeh Kontorovich ()

Causal structure-based root cause analysis of outliers
Kailash Budhathoki (Amazon Research Tübingen) · Dominik Janzing (Amazon) · Patrick Bloebaum (Amazon AWS) · Lenon Minorics (Amazon Research, Tuebingen)

Probabilistic ODE Solutions in Millions of Dimensions
Nicholas Krämer (University of Tübingen) · Nathanael Bosch (University of Tübingen) · Jonathan Schmidt (University of Tübingen) · Philipp Hennig (University of Tuebingen)

Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity
Jingzhao Zhang (Tsinghua University) · Hongzhou Lin (Amazon) · Subhro Das (MIT-IBM Watson AI Lab, IBM Research) · Suvrit Sra (MIT) · Ali Jadbabaie (Massachusetts Institute of Technology)

Feature Space Particle Inference for Neural Network Ensembles
Shingo Yashima (Denso IT Laboratory, inc.) · Teppei Suzuki (Denso IT Laboratory) · Kohta Ishikawa (DENSO IT Laboratory) · Ikuro Sato (Tokyo Institute of Technology / Denso IT Laboratory) · Rei Kawakami (Tokyo Institute of Technology / Denso IT Laboratory)

Generalized Leverage Scores: Geometric Interpretation and Applications
Bruno Ordozgoiti (Queen Mary University of London) · Antonis Matakos (Aalto University) · Aristides Gionis (KTH Royal Institute of Technology)

Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
Ruize Gao (The Chinese University of Hong Kong) · Jiongxiao Wang (Fudan University) · Kaiwen Zhou (The Chinese University of Hong Kong) · Feng Liu (The University of Melbourne) · Binghui Xie (The Chinese University of Hong Kong) · Gang Niu (RIKEN) · Bo Han (HKBU / RIKEN) · James Cheng (CUHK)

Functional Output Regression with Infimal Convolution: Exploring the Huber and $\epsilon$-insensitive Losses
Alex Lambert (KU Leuven) · Dimitri Bouche (Télécom Paris) · Zoltan Szabo (London School of Economics) · Florence d'Alché-Buc (Télécom Paris, Institut Polytechnique de Paris)

Neural Laplace: Learning diverse classes of differential equations in the Laplace domain
Samuel Holt (Cambridge University) · Zhaozhi Qian (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

Fast Provably Robust Decision Trees and Boosting
Jun-Qi Guo (Nanjing University) · Ming-Zhuo Teng (Nanjing University) · Wei Gao (Nanjing University) · Zhi-Hua Zhou (Nanjing University)

Sparse Double Descent: Where Network Pruning Aggravates Overfitting
Zheng He (Beihang University) · Zeke Xie (The University of Tokyo/RIKEN AIP) · Quanzhi Zhu (Beihang university) · Zengchang Qin (Intelligent Computing & Machine Learning Lab, School of ASEE, Beihang University)

Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror Descent
Weiming Liu (University of Science and Technology of China) · Huacong Jiang (University of Science and Technology of China) · Bin Li (University of Science and Technology of China) · Houqiang Li (University of Science and Technology of China)

A Resilient Distributed Boosting Algorithm
Idan Mehalel (Technion) · Yuval filmus (Technion) · Shay Moran (-)

How Powerful are Spectral Graph Neural Networks
Xiyuan Wang (Peking University) · Muhan Zhang (Peking University)

Fast and Provable Nonconvex Tensor RPCA
Haiquan Qiu (Xi'an Jiaotong University) · Yao Wang () · Shaojie Tang (University of Texas at Dallas) · Deyu Meng () · QUANMING YAO (4Paradigm)

Equivariant Diffusion for Molecule Generation in 3D
Emiel Hoogeboom (University of Amsterdam) · Victor Garcia Satorras (Microsoft) · Clément Vignac (EPFL) · Max Welling (University of Amsterdam & Qualcomm)

Optimizing Tensor Network Contraction Using Reinforcement Learning
eli meirom (NVIDIA) · Haggai Maron (NVIDIA Research) · Shie Mannor (Technion) · Gal Chechik (NVIDIA / Bar-Ilan University)

An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings
Meyer Scetbon (CREST, ENSAE) · Laurent Meunier (Dauphine University - FAIR Paris) · Yaniv Romano (Technion---Israel Institute of Technology)

Adaptive Gaussian Process Change Point Detection
Edoardo Caldarelli (Institut de Robòtica i Informàtica Industrial, CSIC-UPC) · Philippe Wenk (ETH Zurich) · Stefan Bauer (KTH Stockholm) · Andreas Krause (ETH Zurich)

Label Ranking through Nonparametric Regression
Dimitris Fotakis (National Technical University of Athens) · Alkis Kalavasis (National Technical University of Athens) · Eleni Psaroudaki (National Technical University of Athens)

On Learning Mixture of Linear Regressions in the Non-Realizable Setting
Soumyabrata Pal (Umass Amherst) · Arya Mazumdar (University of California, San Diego) · Rajat Sen (Google Research) · Avishek Ghosh (University of California, San Diego)

An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
Sadegh Farhadkhani (EPFL) · Rachid Guerraoui (EPFL) · Lê-Nguyên Hoang (EPFL) · Oscar Villemaud (EPFL)

Robust Kernel Density Estimation with Median-of-Means principle
Pierre Humbert (Université Paris Saclay, INRIA) · Batiste Le Bars (Inria) · Ludovic Minvielle (ENS Paris-Saclay)

Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel Convolutions
Eunsang Lee (Seoul National University) · Joon-Woo Lee (Seoul National University) · Junghyun Lee (Seoul National University) · Young-Sik KIM (Chosun University) · Yongjune Kim (DGIST) · Jong-Seon No (Seoul National University) · Woosuk Choi (Samsung Advanced Institute of Technology)

3D Infomax improves GNNs for Molecular Property Prediction
Hannes Stärk (Massachusetts Institute of Technology) · Dominique Beaini (Valence Discovery) · Gabriele Corso (MIT) · Prudencio Tossou ( Valence Discovery ) · Christian Dallago (Technical University of Munich) · Stephan Günnemann (Technical University of Munich) · Pietro Lió (University of Cambridge)

Federated Learning with Label Distribution Skew via Logits Calibration
Jie Zhang (Zhejiang University) · Zhiqi Li (Zhejiang University) · Bo Li (Nanjing University) · Jianghe Xu (Tencent Youtu Lab) · Shuang Wu (Tencent) · Shouhong Ding (Tencent) · Chao Wu (Zhejiang University)

Efficient Learning for Alpha Zero via Path Consistency
Dengwei Zhao (Shanghai Jiao Tong University) · Shikui Tu (Shanghai Jiao Tong University) · Lei Xu (Shanghai Jiao Tong University)

Modeling Irregular Time Series with Continuous Recurrent Units
Mona Schirmer (Bosch Center for AI, University of Amsterdam) · Mazin Eltayeb (Bosch Center for Artificial Intelligence) · Stefan Lessmann (Humboldt University of Berlin) · Maja Rudolph (BCAI)

Virtual Homogeneity Learning
Zhenheng Tang (Hong Kong Baptist University) · Yonggang Zhang (University of Science and Technology of China) · Shaohuai Shi (The Hong Kong University of Science and Technology) · Xin He (Hong Kong Baptist University) · Bo Han (HKBU / RIKEN) · Xiaowen Chu (Hong Kong University of Science and Technology (Guangzhou))

Constraint-based graph network simulator
Yulia Rubanova (Deepmind) · Alvaro Sanchez-Gonzalez (DeepMind) · Tobias Pfaff (DeepMind) · Peter Battaglia (DeepMind)

Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them
Florian Tramer (Google)

Modeling Structure with Undirected Neural Networks
Tsvetomila Mihaylova (Instituto de Telecomunicações, Lisbon, Portugal, 502854200) · Vlad Niculae (University of Amsterdam) · Andre Filipe Torres Martins (Instituto de Telecomunicacoes)

Understanding and Improving Knowledge Graph Embedding for Entity Alignment
Lingbing Guo (Zhejiang University) · Zequn Sun (Nanjing University) · Mingyang Chen (Zhejiang University) · Wei Hu (Nanjing University) · Qiang Zhang (University College London) · Huajun Chen (Zhejiang University)

C-MinHash: Improving Minwise Hashing with Circulant Permutation
Xiaoyun Li (Baidu Research) · Ping Li (Baidu)

A Neural Tangent Kernel Perspective of GANs
Jean-Yves Franceschi (Criteo AI Lab) · Emmanuel de Bézenac (Sorbonne Université) · Ibrahim Ayed (LIP6, Sorbonne Université) · Mickael Chen (valeo.ai) · Sylvain Lamprier (ISIR-SU) · Patrick Gallinari (Sorbonne Universite, Criteo AI Lab)

Online and Consistent Correlation Clustering
Vincent Cohen-Addad (Google) · Silvio Lattanzi (Google) · Andreas Maggiori (EPFL) · Nikos Parotsidis (Google)

Structure-Aware Transformer for Graph Representation Learning
Dexiong Chen (ETH Zurich) · Leslie O'Bray (ETH Zürich) · Karsten Borgwardt (ETH Zurich)

Generative Coarse-Graining of Molecular Conformations
Wujie Wang (Massachusetts Institute of Technology) · Minkai Xu (University of Montreal) · Chen Cai (University of California, San Diego) · Benjamin Kurt Miller (University of Amsterdam) · Tess Smidt (Massachusetts Institute of Technology) · Yusu Wang (UC San Diego) · Jian Tang (Mila) · Rafael Gomez-Bombarelli (MIT)

Deep Safe Incomplete Multi-view Clustering: Theorem and Algorithm
Huayi Tang (Renmin University of China) · Yong Liu (Renmin University of China)

Multi-Task Learning as a Bargaining Game
Aviv Navon (Bar-Ilan University) · Aviv Shamsian (Bar Ilan University) · Idan Achituve (Bar-Ilan) · Haggai Maron (NVIDIA Research) · Kenji Kawaguchi (National University of Singapore) · Gal Chechik (NVIDIA / Bar-Ilan University) · Ethan Fetaya (Bar-Ilan University)

Minimax rate of consistency for linear models with missing values
Alexis Ayme (Sorbonne Université) · Claire Boyer (LPSM, Sorbonne Université) · Aymeric Dieuleveut (École polytechnique) · Erwan Scornet (École Polytechnique)

DNNR: Differential Nearest Neighbors Regression
Youssef Nader (Freie Universitat Berlin) · Leon Sixt (Freie Universität Berlin) · Tim Landgraf (Freie Universität Berlin)

Fair Generalized Linear Models with a Convex Penalty
Hyungrok Do (NYU Grossman School of Medicine) · Preston Putzel (University of California-Irvine) · Axel Martin (NYU Langone) · Padhraic Smyth (University of California, Irvine) · Judy Zhong (NYU School of Medicine)

Measuring dissimilarity with diffeomorphism invariance
Théophile Cantelobre (Inria) · Carlo Ciliberto (University College London) · Benjamin Guedj (Inria and University College London) · Alessandro Rudi (INRIA, École Normale Supérieure)

Deep Squared Euclidean Approximation to the Levenshtein Distance for DNA Storage
Alan J.X. Guo (Tianjin University) · Cong Liang (Tianjin University) · Qing-Hu Hou (Tianjin University)

Datamodels: Understanding Predictions with Data and Data with Predictions
Andrew Ilyas (Massachusetts Institute of Technology) · Sung Min (Sam) Park (MIT) · Logan Engstrom (MIT) · Guillaume Leclerc (MIT) · Aleksander Madry (MIT)

A Consistent and Efficient Evaluation Strategy for Attribution Methods
Tobias Leemann (University of Tübingen) · Yao Rong (University of Tübingen) · Vadim Borisov (The University of Tuebingen) · Gjergji Kasneci ( University of Tuebingen) · Enkelejda Kasneci (University of Tuebingen)

Understanding the unstable convergence of gradient descent
Kwangjun Ahn (MIT EECS) · Jingzhao Zhang (Tsinghua University) · Suvrit Sra (MIT)

Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding
Lan-Zhe Guo (Nanjing University) · Yu-Feng Li (Nanjing University)

Local Linear Convergence of Douglas-Rachford for Linear Programming: a Probabilistic Analysis
Oisin Faust (University of Cambridge) · Hamza Fawzi (University of Cambridge)

When and How Mixup Improves Calibration: A Theoretical View
Linjun Zhang (Rutgers University) · Zhun Deng (Harvard) · Kenji Kawaguchi (National University of Singapore) · James Zou (Stanford University)

Least Squares Estimation using Sketched Data with Heteroskedastic Errors
Sokbae Lee (Columbia University) · Serena Ng (Columbia University)

Random Forest Density Estimation
Hongwei Wen (University of Twente) · Hanyuan Hang (University of Twente)

Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Pihe Hu (IIIS, Tsinghua University) · Yu Chen (Tsinghua University) · Longbo Huang (Tsinghua University)

Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training
Jan Kaiser (Deutsches Elektronen-Synchrotron DESY) · Oliver Stein (Deutsches Elektronen-Synchrotron DESY) · Annika Eichler (Deutsches Elektronen-Synchrotron DESY)

Causal Imitation Learning under Temporally Correlated Noise
Gokul Swamy (Carnegie Mellon University) · Sanjiban Choudhury (Cornell University) · James Bagnell (Aurora Innovation) · Steven Wu (Carnegie Mellon University)

Out-of-distribution Detection with Deep Nearest Neighbors
Yiyou Sun (University of Wisconsin Madison) · Yifei Ming (University of Wisconsin-Madison) · Jerry Zhu (University of Wisconsin-Madison) · Yixuan Li (University of Wisconsin-Madison)

Deciphering Lasso-based Classification Through a Large Dimensional Analysis of the Iterative Soft-Thresholding Algorithm
Malik TIOMOKO (Huawei Technologies) · Ekkehard Schnoor (RWTH Aachen University) · Mohamed El Amine Seddik (Huawei) · Igor Colin (Huawei Technologies) · Aladin Virmaux (Huawei)

From data to functa: Your data point is a function and you should treat it like one
Emilien Dupont (University of Oxford) · Hyunjik Kim (DeepMind) · S. M. Ali Eslami (DeepMind) · Danilo J. Rezende (DeepMind) · Dan Rosenbaum (DeepMind)

Unifying Modalities, Tasks, and Architectures Through a Simple Sequence-to-Sequence Learning Framework
Peng Wang (Alibaba Group) · An Yang (Alibaba Group) · Rui Men (Alibaba Group) · Junyang Lin (Alibaba Group) · Shuai Bai (Alibaba Group) · Zhikang Li (DAMO Academy, Alibaba Group) · Jianxin Ma (Alibaba Group) · Chang Zhou (Alibaba Group) · Jingren Zhou (Alibaba Group) · Hongxia Yang (Alibaba Group)

GMC - Geometric Contrastive Multimodal Representation Learning
Petra Poklukar (KTH Royal Institute of Technology) · Miguel Vasco (INESC-ID & Instituto Superior Técnico, University of Lisbon) · Hang Yin (KTH) · Francisco S. Melo (IST/INESC-ID) · Ana Paiva (INESC-ID U of Lisbon) · Danica Kragic (KTH)

Generative Cooperative Networks for Natural Language Generation
Sylvain Lamprier (ISIR-SU) · Thomas Scialom (reciTAL) · Antoine Chaffin (CNRS-UMR6074-IMATAG, IRISA) · Vincent Claveau (IRISA) · Ewa Kijak (IRISA) · Jacopo Staiano (reciTAL) · Benjamin Piwowarski (Sorbonne Université)

On the Equivalence Between Temporal and Static Equivariant Graph Representations
Jianfei Gao (Purdue University) · Bruno Ribeiro (Purdue University)

Generalized Data Distribution Iteration
Jiajun Fan (Tsinghua University) · Changnan Xiao (ByteDance)

A Completely Tuning-Free and Robust Approach to Sparse Precision Matrix Estimation
Chau Tran (University of California, Santa Barbara) · Guo Yu (University of California Santa Barbara)

Optimization-induced Implicit Graph Diffusion
Qi Chen (Peking University) · Yifei Wang (Peking University) · Yisen Wang (Peking University) · Jiansheng Yang (Peking University) · Zhouchen Lin (Peking University)

Revisiting Consistency Regularization for Deep Partial Label Learning
Dong-Dong Wu (Southeast University) · Deng-Bao Wang (Southeast University) · Min-Ling Zhang (Southeast University)

Bounding the Width of Neural Networks via Coupled Initialization - A Worst Case Analysis
Alexander Munteanu (TU Dortmund) · Simon Omlor (TU Dortmund) · Zhao Song (Adobe Research) · David Woodruff (Carnegie Mellon University)

Spectral Representation of Robustness Measures for Optimization Under Input Uncertainty
Jixiang Qing (Ghent University) · Ivo Couckuyt (Ghent University - imec) · Tom Dhaene (Ghent University - imec)

Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language
Iou-Jen Liu (University of Illinois at Urbana-Champaign) · Xingdi Yuan (Microsoft Research, Montreal) · Marc-Alexandre Côté (Microsoft Research) · Pierre-Yves Oudeyer (Inria) · Alex Schwing (University of Illinois)

Causal Transformer for Estimating Counterfactual Outcomes
Valentyn Melnychuk (LMU Munich) · Dennis Frauen (LMU Munich) · Stefan Feuerriegel (LMU Munich)

DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck
Jiameng Fan (Boston University) · Wenchao Li (Boston University)

On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions
Lai Tian (The Chinese University of Hong Kong) · Kaiwen Zhou (The Chinese University of Hong Kong) · Anthony Man-Cho So (The Chinese University of Hong Kong)

From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers
Krzysztof Choromanski (Google Brain Robotics) · Han Lin (Columbia University) · Haoxian Chen (Columbia University) · Tianyi Zhang (Columbia University) · Arijit Sehanobish (Covera Health) · Valerii Likhosherstov (University of Cambridge) · Jack Parker-Holder (University of Oxford) · Tamas Sarlos (Google) · Adrian Weller (University of Cambridge, Alan Turing Institute) · Thomas Weingarten (Google)

Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy
ZHIHAN LIU (Northwestern University) · Lu Miao (University of Science and Technology of China) · Zhaoran Wang (Northwestern University) · Michael Jordan (UC Berkeley) · Zhuoran Yang (Yale University)

A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines
Weichao Zhou (Boston University) · Wenchao Li (Boston University)

Cycle Representation Learning for Inductive Relation Prediction
Zuoyu Yan (Peking University) · Tengfei Ma (IBM Research) · Liangcai Gao (Peking University) · Zhi Tang (Peking University) · Chao Chen (Stony Brook University)

Learning Iterative Reasoning through Energy Minimization
Yilun Du (MIT) · Shuang Li (MIT) · Josh Tenenbaum (MIT) · Igor Mordatch (Google Brain)

Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension
Bruno Loureiro (EPFL) · Cedric Gerbelot (ENS) · Maria Refinetti (Laboratoire de Physique de l’Ecole Normale Supérieure Paris) · Gabriele Sicuro (King's College London) · FLORENT KRZAKALA (EPFL)

Inductive Biases and Variable Creation in Self-Attention Mechanisms
Benjamin Edelman (Harvard University) · Surbhi Goel (Microsoft Research) · Sham Kakade (Harvard University) · Cyril Zhang (Microsoft Research)

Weisfeiler-Lehman meets Gromov-Wasserstein
Samantha Chen (UCSD) · Sunhyuk Lim (Max Planck Institute for Mathematics in the Sciences) · Facundo Memoli (Ohio State University) · Zhengchao Wan (UCSD) · Yusu Wang (UC San Diego)

Self-Organized Polynomial-Time Coordination Graphs
Qianlan Yang (Tsinghua University) · Weijun Dong (Tsinghua University) · Zhizhou Ren (University of Illinois at Urbana-Champaign) · Jianhao Wang (Tsinghua University) · Tonghan Wang (Tsinghua University) · Chongjie Zhang (Tsinghua University)

Bregman Power k-Means for Clustering Exponential Family Data
Adithya D Vellal (Duke University) · Saptarshi Chakraborty (UC Berkeley) · Jason Xu (Duke University)

Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
Uri Alon (Carnegie Mellon University) · Frank Xu (Carnegie Mellon University) · Junxian He (Carnegie Mellon University) · Sudipta Sengupta (Amazon Web Services) · Dan Roth (University of Pennsylvania and AWS AI Labs) · Graham Neubig (Carnegie Mellon University)

Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation
ZHIHAN LIU (Northwestern University) · Yufeng Zhang (Northwestern University) · Zuyue Fu (Northwestern.edu) · Zhuoran Yang (Yale University) · Zhaoran Wang (Northwestern University)

Flashlight: Enabling Innovation in Tools for Machine Learning
Jacob Kahn (Facebook AI Research (FAIR)) · Vineel Pratap (Facebook) · Tatiana Likhomanenko (Apple) · Qiantong Xu (Facebook AI Research) · Awni Hannun (Zoom AI) · Jeff Cai (None) · Paden Tomasello (Facebook AI Research) · Ann Lee (Facebook, Inc.) · Edouard Grave (Facebook AI Research) · Gilad Avidov (Facebook) · Benoit Steiner (FAIR) · Vitaliy Liptchinsky (Facebook) · Gabriel Synnaeve (Facebook AI Research) · Ronan Collobert (Facebook AI Research)

A psychological theory of explainability
Nils Erik Tomas Folke (Rutgers) · Scott Cheng-Hsin Yang (Rutgers University) · Patrick Shafto (IAS / Rutgers University)

Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets
Tal Shnitzer (MIT) · Mikhail Yurochkin (IBM Research, MIT-IBM Watson AI Lab) · Kristjan Greenewald (IBM) · Justin Solomon (MIT)

The Importance of Non-Markovianity in Maximum State Entropy Exploration
Mirco Mutti (Politecnico di Milano, Università di Bologna) · Riccardo De Santi (ETH Zurich ) · Marcello Restelli (Politecnico di Milano)

Parsimonious Learning-Augmented Caching
Sungjin Im (University of California, Merced) · Ravi Kumar (Google) · Aditya Petety (University of California Merced) · Manish Purohit (Google Research)

Robustness Verification for Contrastive Learning
Zekai Wang (Wuhan University) · Weiwei Liu (Wuhan University)

Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness
Adam Foster (Microsoft Research) · Arpi Vezer (BenevolentAI) · Craig Glastonbury (Human Technopole) · Páidí Creed (Cambridge Epigenetix) · Sam Abujudeh (BenevolentAI) · Aaron Sim (BenevolentAI)

Fenrir: Physics-Enhanced Regression for Initial Value Problems
Filip Tronarp (University of Tübingen) · Nathanael Bosch (University of Tübingen) · Philipp Hennig (University of Tuebingen)

A Model-Agnostic Randomized Learning Framework based on Random Hypothesis Subspace Sampling
Yiting Cao (University of Oklahoma) · Chao Lan (University of Oklahoma)

Efficient Online ML API Selection for Multi-Label Classification Tasks
Lingjiao Chen (University of Wisconsin-Madison) · Matei Zaharia (Stanford and Databricks) · James Zou (Stanford University)

IDYNO: Learning Nonparametric DAGs from Interventional Dynamic Data
Tian Gao (IBM Research) · DEBARUN BHATTACHARJYA (IBM Research) · Elliot Nelson (IBM Research) · Miao Liu (IBM) · Yue Yu (Lehigh University)

Toward Compositional Generalization in Object-Oriented World Modeling
Linfeng Zhao (Northeastern University) · Lingzhi Kong (Northeastern University) · Robin Walters (Northeastern University) · Lawson Wong (Northeastern University)

Gradient based clustering
Aleksandar Armacki (Carnegie Mellon University) · Dragana Bajovic (University of Novi Sad) · Dusan Jakovetic (University of Novi Sad) · Soummya Kar (Carnegie Mellon University)

Breaking Down Out-of-Distribution Detection: Many Popular Methods Estimate a Combination of the Same Core Quantities
Julian Bitterwolf (University of Tübingen) · Alexander Meinke (University of Tübingen) · Maximilian Augustin (University of Tuebingen) · Matthias Hein (University of Tübingen)

On the Statistical Benefits of Curriculum Learning
Ziping Xu (University of Michigan) · Ambuj Tewari (University of Michigan)

Towards Scaling Difference Target Propagation by Learning Backprop Targets
Maxence ERNOULT (IBM Research) · Fabrice Normandin (Mila) · Abhinav Moudgil (Mila, Concordia University) · Sean Spinney (Mila) · Eugene Belilovsky (Mila) · Irina Rish (MILA / Université de Montréal h) · Blake Richards (Mila) · Yoshua Bengio (Mila - Quebec AI Institute)

How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective
Akhilan Boopathy (MIT) · Ila R. Fiete (MIT)

General-purpose, long-context autoregressive modeling with Perceiver AR
Curtis Hawthorne (Google Brain) · Andrew Jaegle (DeepMind) · Cătălina Cangea (DeepMind) · Sebastian Borgeaud (DeepMind) · Charlie Nash (DeepMind) · Mateusz Malinowski (DeepMind) · Sander Dieleman (DeepMind) · Oriol Vinyals (Google DeepMind) · Matthew Botvinick (DeepMind) · Ian Simon (Google Brain) · Hannah Sheahan (DeepMind) · Neil Zeghidour (Google) · Jean-Baptiste Alayrac (DeepMind) · Joao Carreira (DeepMind) · Jesse Engel (Google Brain)

Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional data
Umberto M. Tomasini (EPFL) · Antonio Sclocchi (EPFL - IPHYS - PCSL) · Matthieu Wyart ()

FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning
Anis Elgabli (University of Oulu) · Chaouki Ben Issaid (University of Oulu) · Amrit Singh Bedi (University of Maryland, College Park) · Ketan Rajawat (Indian Institute of Technology Kanpur) · Mehdi Bennis (University of Oulu) · Vaneet Aggarwal (Purdue University)

PDE-Based Optimal Strategy for Unconstrained Online Learning
Zhiyu Zhang (Boston University) · Ashok Cutkosky (Boston University) · Ioannis Paschalidis (Boston University)

Training OOD Detectors in Their Natural Habitats
Julian Katz-Samuels (University of Wisconsin) · Julia Nakhleh (University of Wisconsin-Madison) · Yixuan Li (University of Wisconsin-Madison) · Robert Nowak (University of Wisconsion-Madison)

Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence
Zi-Hao Qiu (Nanjing University) · Quanqi Hu (University of Iowa) · Yongjian Zhong (The University of Iowa) · Lijun Zhang (Nanjing University) · Tianbao Yang (The University of Iowa)

Conformal Prediction Sets with Limited False Positives
Adam Fisch (MIT) · Tal Schuster (Google) · Tommi Jaakkola (MIT) · Regina Barzilay (MIT CSAIL)

Learning to Infer Structures of Network Games
Emanuele Rossi (Twitter) · Federico Monti (Fabula AI) · Yan Leng (University of Texas at Austin) · Michael Bronstein (Imperial College / Twitter) · Xiaowen Dong (Oxford)

NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks
Mustafa Burak Gurbuz (Georgia Institute of technology) · Constantine Dovrolis (Georgia Tech)

Dialog Inpainting: Inferring two-speaker QA dialogs from single-author documents at web scale
Zhuyun Dai (Google) · Arun Tejasvi Chaganty (Google) · Vincent Zhao (Google AI Language) · Aida Amini (University of Washington) · Qazi Mamunur Rashid (Google) · Mike Green (Google) · Kelvin Guu (Google)

Domain Adaptation for Time Series Forecasting via Attention Sharing
Xiaoyong Jin (UCSB) · Youngsuk Park (Amazon Research) · Danielle Robinson (Amazon Web Services) · Hao Wang (Rutgers University) · Yuyang Wang (AWS AI Labs)

On the Adversarial Robustness of Causal Algorithmic Recourse
Ricardo Dominguez-Olmedo (University of Tübingen) · Amir Karimi (MPI for Intelligent Systems, Tübingen, Germany) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Learning Dynamics and Generalization in Reinforcement Learning
Clare Lyle (University of Oxford) · Mark Rowland (DeepMind) · Will Dabney (DeepMind) · Marta Kwiatkowska (Oxford University) · Yarin Gal (University of Oxford)

A query-optimal algorithm for finding counterfactuals
Guy Blanc (Stanford University) · Caleb Koch (Stanford University) · Jane Lange (MIT) · Li-Yang Tan (Stanford University)

Reverse Engineering $\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees
Darshan Thaker (Johns Hopkins University) · Paris Giampouras (Mathematical Institute for Data Science, Johns Hopkins University) · Rene Vidal (Johns Hopkins University, USA)

Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation Learning
Max Paulus (ETH Zurich) · Giulia Zarpellon (Vector Institute) · Andreas Krause (ETH Zurich) · Laurent Charlin (Mila) · Chris Maddison (University of Toronto)

Model-Free Opponent Shaping
Christopher Lu (University of Oxford) · Timon Willi (University of Oxford) · Christian Schroeder de Witt (University of Oxford) · Jakob Foerster (Oxford university)

Benefits of Deep and Wide Convolutional Residual Networks: Function Approximation under Smoothness Constraint
Hao Liu (Hong Kong Baptist University) · Minshuo Chen (Georgia Tech) · Siawpeng Er (Georgia Institute of Technology) · Wenjing Liao (Georgia Tech) · Tong Zhang (HKUST) · Tuo Zhao (Georgia Tech)

Stochastic Rising Bandits
Alberto Maria Metelli (Politecnico di Milano) · Francesco Trovò (Politecnico di Milano) · Matteo Pirola (Politecnico di Milano) · Marcello Restelli (Politecnico di Milano)

A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions
Daniel Lundstrom (University of Southern California) · Tianjian Huang (University of Southern California) · Meisam Razaviyayn (University of southern California)

Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations
Qingyang Tan (University of Maryland, College Park) · Zherong Pan (Tencent America) · Breannan Smith (Meta Reality Labs Research) · Takaaki Shiratori (Meta Reality Labs Research) · Dinesh Manocha (University of Maryland at College Park)

On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning
Weichao Mao (University of Illinois Urbana-Champaign) · Lin Yang (UCLA) · Kaiqing Zhang (MIT) · Tamer Basar (University of Illinois at Urbana-Champaign)

Sample-Efficient Reinforcement Learning for POMDPs with Linear Function Approximations
Qi Cai (Northwestern University) · Zhuoran Yang (Yale University) · Zhaoran Wang (Northwestern University)

Improving Generic Models for Image-Goal Navigation
Arjun Majumdar (Georgia Institute of Technology) · Gunnar Sigurdsson (Amazon) · Robinson Piramuthu (Amazon Inc) · Jesse Thomason (University of Southern California) · Dhruv Batra (Georgia Institute of Technology / Facebook AI Research) · Gaurav Sukhatme (University of Southern California)

Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent
Sharan Vaswani (Simon Fraser University) · Benjamin Dubois-Taine (CNRS, ENS Paris, Inria) · Reza Babanezhad (Samsung)

A Stochastic Multi-Rate Control Framework For Modeling Distributed Optimization Algorithms
xinwei zhang (University of Minnesota) · Mingyi Hong (University of Minnesota) · Sairaj Dhople (University of Minnesota) · Nicola Elia (University of Minnesota)

Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass
Giorgia Dellaferrera (Harvard Medical School, Boston Children's Hospital) · Gabriel Kreiman (Harvard Medical School)

Solving Catastrophic Forgetting via Weight Interval Constraints
Maciej Wołczyk (Jagiellonian University) · Karol J. Piczak (Jagiellonian University) · Bartosz Wójcik (Jagiellonian University) · Łukasz Pustelnik (Jagiellonian University) · Paweł Morawiecki (Institute of Computer Science, Polish Academy of Sciences) · Jacek Tabor (Jagiellonian University in Kraków) · Tomasz Trzcinski (Warsaw University of Technology, Tooploox) · Przemysław Spurek (Jagiellonian University)

GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Alexander Nichol (OpenAI) · Prafulla Dhariwal (OpenAI) · Aditya Ramesh (OpenAI) · Pranav Shyam (OpenAI) · Pamela Mishkin (OpenAI) · Bob McGrew (OpenAI) · Ilya Sutskever (OpenAI) · Mark Chen (OpenAI)

A Simple Guard for Learned Optimizers
Isabeau Prémont-Schwarz (Good AI) · Jaroslav Vítků (GoodAI) · Jan Feyereisl (GoodAI)

Deletion Robust Submodular Maximization over Matroids
PAUL DUETTING (Google) · Federico Fusco (Sapienza University of Rome) · Silvio Lattanzi (Google) · Ashkan Norouzi-Fard (Google) · Morteza Zadimoghaddam (Google)

Probabilistically Robust Learning: Balancing Average- and Worst-case Performance
Alex Robey (University of Pennsylvania) · Luiz F. O. Chamon (University of California, Berkeley) · George J. Pappas (University of Pennsylvania) · Hamed Hassani (University of Pennsylvania)

Probabilistic Inverse Optimal Transport
Wei-Ting Chiu (Rutgers University - Newark) · Pei Wang (Rutgers University-Newark) · Patrick Shafto (IAS / Rutgers University)

Learning Symmetric Embeddings for Equivariant World Models
Jung Yeon Park (Northeastern University) · Ondrej Biza (Northeastern University) · Linfeng Zhao (Northeastern University) · Jan-Willem van de Meent (University of Amsterdam) · Robin Walters (Northeastern University)

Generalized Federated Learning via Sharpness Aware Minimization
Zhe Qu (University of South Florida) · Xingyu Li (Mississippi State University) · Rui Duan (University of South Florida) · Zhuo Lu (University of South Florida) · Yao Liu (University of South Florida) · Bo Tang (Mississippi State University)

Stability Based Generalization Bounds for Exponential Family Langevin Dynamics
Arindam Banerjee (UIUC) · Tiancong Chen (University of Minnesota) · Xinyan Li (University of Minnesota, Twin Cities) · Yingxue Zhou (University of Minnesota)

Congested Bandits: Optimal Routing via Short-term Resets
Pranjal Awasthi (Google) · Kush Bhatia (UC Berkeley) · Sreenivas Gollapudi (Google Research) · Kostas Kollias (Google Research)

Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance
Zhuoning Yuan (The University of Iowa) · Yuexin Wu (Google) · Zi-Hao Qiu (Nanjing University) · Xianzhi Du (Google Inc.) · Lijun Zhang (Nanjing University) · Denny Zhou (Google Brain) · Tianbao Yang (The University of Iowa)

Certified Neural Network Watermarks with Randomized Smoothing
Arpit Bansal (University of Maryland, College Park) · Ping-yeh Chiang (University of Maryland, College Park) · Michael Curry (University of Maryland College Park) · Rajiv Jain (Adobe Research) · Curtis Wigington (Adobe Research) · Varun Manjunatha (Adobe Research) · John P Dickerson (Arthur AI & Univ. of Maryland) · Tom Goldstein (University of Maryland)

What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us?
Tiffany Vlaar (University of Edinburgh) · Jonathan Frankle (MosaicML / Harvard)

Multirate Training of Neural Networks
Tiffany Vlaar (University of Edinburgh) · Benedict Leimkuhler (University of Edinburgh)

Private frequency estimation via projective geometry
Vitaly Feldman (Apple) · Jelani Nelson (UC Berkeley) · Huy Nguyen (Northeastern University) · Kunal Talwar (Apple)

Improving Task-free Continual Learning by Distributionally Robust Memory Evolution
Zhenyi Wang (University at Buffalo) · Li Shen (JD Explore Academy) · Le Fang (University at Buffalo-SUNY) · Qiuling Suo (State University of New York at Buffalo) · Tiehang Duan (State University of New York at Buffalo) · Mingchen Gao (University at Buffalo, SUNY)

SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching
Jason Yecheng Ma (University of Pennsylvania) · Andrew Shen (University of Melbourne) · Dinesh Jayaraman (University of Pennsylvania) · Osbert Bastani (University of Pennsylvania)

Convergence of Uncertainty Sampling for Active Learning
Anant Raj (INRIA- ENS and UIUC) · Francis Bach (INRIA - Ecole Normale Supérieure)

Revisiting End-to-End Speech-to-Text Translation From Scratch
Biao Zhang (University of Edinburgh) · Barry Haddow () · Rico Sennrich (University of Zurich)

Data Augmentation as Feature Manipulation: a story of desert cows and grass cows
Ruoqi Shen (University of Washington) · Sebastien Bubeck (Microsoft Research) · Suriya Gunasekar (Microsoft Research)

Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations
Mohammad Mahmudul Alam (University of Maryland, Baltimore County) · Edward Raff (Booz Allen Hamilton) · Tim Oates (University Of Maryland Baltimore County) · James Holt (Laboratory for Physical Sciences)

Examining Scaling and Transfer of Language Model Architectures for Machine Translation
Biao Zhang (University of Edinburgh) · Behrooz Ghorbani (Google Research) · Ankur Bapna (Google Research) · Yong Cheng (Google) · Xavier Garcia (Google) · Jonathan Shen (Independent) · Orhan Firat (Google)

Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes
Insu Han (Yale University) · Mike Gartrell (Criteo AI Lab) · Elvis Dohmatob (Meta) · Amin Karbasi (Yale)

Unified Scaling Laws for Routed Language Models
Aidan Clark (OpenAI) · Diego de Las Casas (DeepMind) · Aurelia Guy (Google Inc.) · Arthur Mensch (Deepmind) · Michela Paganini (DeepMind) · Jordan Hoffmann (DeepMind) · Bogdan Damoc (DeepMind) · Blake Hechtman (Google) · Trevor Cai (DeepMind) · Sebastian Borgeaud (DeepMind) · George van den Driessche (DeepMind) · Eliza Rutherford (DeepMind) · Tom Hennigan (DeepMind) · Matthew Johnson (Google Brain) · Albin Cassirer (DeepMind) · Chris Jones (DeepMind) · Elena Buchatskaya (DeepMind) · David Budden (DeepMind) · Laurent Sifre (DeepMind) · Simon Osindero (DeepMind) · Oriol Vinyals (Google DeepMind) · Marc'Aurelio Ranzato (Deepmind) · Jack Rae (DeepMind) · Erich Elsen (Google) · Koray Kavukcuoglu (DeepMind) · Karen Simonyan (Inflection AI)

Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization
Xiaojun Xu (University of Illinois at Urbana-Champaign) · Yibo Zhang (University of Illinois at Urbana-Champaign) · Evelyn Ma (UIUC) · Hyun Ho Son (University of Illinois Urbana-Champaign) · Sanmi Koyejo (UIUC) · Bo Li (UIUC)

Certified Robustness Against Natural Language Attacks by Causal Intervention
Haiteng Zhao (Peking University) · Chang Ma (Peking University) · Xinshuai Dong (Xiamen University) · Anh Tuan Luu (Nanyang Technological University) · Zhi-Hong Deng (Peking University) · Hanwang Zhang (Nanyang Technological University)

First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach
Andrew Wagenmaker (University of Washington) · Yifang Chen (University of Washington) · Max Simchowitz (MIT) · Simon Du (University of Washington) · Kevin Jamieson (University of Washington)

Contextual Bandits with Large Action Spaces: Made Practical
Yinglun Zhu (University of Wisconsin-Madison) · Dylan Foster (Microsoft Research) · John Langford (Microsoft Research) · Paul Mineiro (Microsoft)

PINs: Progressive Implicit Networks for Multi-Scale Neural Representations
Zoe Landgraf (Meta (FAIAR)) · Alexander Sorkine Hornung (Meta) · ricardo cabral (meta)

Bayesian Nonparametrics for Offline Skill Discovery
Valentin Villecroze (Layer 6) · Harry Braviner (Layer 6 AI) · Panteha Naderian (Layer 6 AI) · Chris Maddison (University of Toronto) · Gabriel Loaiza-Ganem (Layer 6 AI)

Understanding Doubly Stochastic Clustering
Tianjiao Ding (Johns Hopkins University) · Derek Lim (MIT) · Rene Vidal (Johns Hopkins University, USA) · Benjamin Haeffele (Johns Hopkins University)

ButterflyFlow: Building Invertible Layers with Butterfly Matrices
Chenlin Meng (Stanford University) · Linqi Zhou (University of California, Los Angeles) · Kristy Choi (Stanford University) · Tri Dao (Stanford) · Stefano Ermon (Stanford University)

Self-supervised models of audio effectively explain human cortical responses to speech
Aditya Vaidya (University of Texas at Austin) · Shailee Jain (The University of Texas at Austin) · Alexander Huth (The University of Texas at Austin)

Entropic Causal Inference: Graph Identifiability
Spencer Compton (MIT) · Kristjan Greenewald (IBM) · Dmitriy Katz (IBM Research) · Murat Kocaoglu (Purdue University)

GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
Nan Du (Google) · Yanping Huang (Google Brain) · Andrew Dai (Google) · Simon Tong (Google Brain) · Dmitry Lepikhin (Google) · Yuanzhong Xu (Google) · Maxim Krikun (Google) · Yanqi Zhou (Google) · Adams Wei Yu (Google Brain) · Orhan Firat (Google) · Barret Zoph (Google) · William Fedus (Google Brain) · Maarten Bosma (Google) · Zongwei Zhou (Google Inc.) · Tao Wang (Google Inc.) · Emma Wang (Google) · Kellie Webster (Google) · Marie Pellat (Google) · Kevin Robinson (Google) · Kathleen Meier-Hellstern (Google) · Toju Duke (Google) · Lucas Dixon (Google) · Kun Zhang (Google) · Quoc Le (Google Brain) · Yonghui Wu (Google) · Zhifeng Chen (Google) · Claire Cui (Google)

MAML and ANIL Provably Learn Representations
Liam Collins (University of Texas at Austin) · Aryan Mokhtari (UT Austin) · Sewoong Oh (University of Washington) · Sanjay Shakkottai (University of Texas at Austin)

Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points
Yi Wang (Johns Hopkins University) · Zhiren Wang (Pennsylvania State University)

Kernel Methods for Radial Transformed Compositional Data with Many Zeros
Junyoung Park (KAIST) · Changwon Yoon (Korea Advanced Institute of Science and Technology) · Cheolwoo Park (KAIST) · Jeongyoun Ahn (Korea Advanced Institute of Science and Technology)

Nearly Optimal Catoni’s M-estimator for Infinite Variance
Sujay Bhatt (Baidu Research) · Guanhua Fang (Baidu USA) · Ping Li (Baidu Research) · Gennady Samorodnitsky (Cornell University)

How to Leverage Unlabeled Data in Offline Reinforcement Learning?
Tianhe (Kevin) Yu (Stanford University) · Aviral Kumar (UC Berkeley) · Yevgen Chebotar (Google) · Karol Hausman (Google Brain) · Chelsea Finn (Stanford) · Sergey Levine (UC Berkeley)

Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games
Siqi Liu (DeepMind) · Marc Lanctot (DeepMind) · Luke Marris (DeepMind) · Nicolas Heess (DeepMind)

Variational On-the-Fly Personalization
Jangho Kim (Qualcomm Korea YH) · Jun-Tae Lee (Qualcomm AI Research) · Simyung Chang (Qualcomm Korea YH) · NOJUN KWAK (Seoul National University)

Towards Optimal Exploration in Linear Markov Decision Processes: Covering and Dimension-Optimal PAC
Andrew Wagenmaker (University of Washington) · Yifang Chen (University of Washington) · Max Simchowitz (MIT) · Simon Du (University of Washington) · Kevin Jamieson (University of Washington)

Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture Models
Tudor Manole (Carnegie Mellon University) · Nhat Ho (University of Texas at Austin)

Molecular Graph Representation Learning via Heterogeneous Motif Graph Construction
Zhaoning Yu (Iowa state university) · Hongyang Gao (Iowa State University)

Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
Daniel Vial (UT Austin / UIUC) · Advait Parulekar (University of Texas at Austin) · Sanjay Shakkottai (University of Texas at Austin) · R Srikant (UIUC)

Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks
Nan Wu (New York University) · Stanislaw Jastrzebski (Molecule.one / Jagiellonian University) · Kyunghyun Cho (New York University, Genentech) · Krzysztof J Geras (New York University)

Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning
Yunfei Li (Tsinghua University) · Tian Gao (Tsinghua University) · Jiaqi Yang (University of California, Berkeley) · Huazhe Xu (Stanford University) · Yi Wu (UC Berkeley)

Dual Perspective of Label-Specific Feature Learning for Multi-Label Classification
Jun-Yi Hang (Southeast University) · Min-Ling Zhang (Southeast University)

Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning
Harley Wiltzer (McGill University, Mila) · David Meger (McGill University) · Marc Bellemare (Google Brain)

Deep Network Approximation in Terms of Intrinsic Parameters
Shijun Zhang (National University of Singapore) · Zuowei Shen (National University of Singapore) · Haizhao Yang (University of Maryland College Park)

The Primacy Bias in Deep Reinforcement Learning
Evgenii Nikishin (Mila, Université de Montréal) · Max Schwarzer (Mila, Université de Montréal) · Pierluca D'Oro (Mila, Université de Montréal) · Pierre-Luc Bacon (Mila) · Aaron Courville (Université de Montréal)

Stabilizing Q-learning with Linear Architectures for Provable Efficient Learning
Andrea Zanette (University of California, Berkeley) · Martin Wainwright (UC Berkeley / Voleon)

Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints
Alina Ene (Boston University) · Huy Nguyen (Northeastern University)

Retroformer: Pushing the Limits of End-to-end Retrosynthesis Transformer
Yue Wan (Tencent) · Chang-Yu (Kim) Hsieh (Tencent) · Shengyu Zhang (Tencent) · Ben Liao (Tencent)

Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
Jingfeng Wu (Johns Hopkins University) · Difan Zou (UCLA) · Vladimir Braverman (Johns Hopkins University) · Quanquan Gu (University of California, Los Angeles) · Sham Kakade (Harvard University)

Optimizing Sequential Experimental Design with Deep Reinforcement Learning
Tom Blau (CSIRO's Data61) · Edwin V Bonilla (CSIRO's Data61) · Iadine Chades (CSIRO) · Amir Dezfouli (CSIRO's Data61)

On the Robustness of CountSketch to Adaptive Inputs
Edith Cohen (Google Research and Tel Aviv University) · Xin Lyu (University of California, Berkeley) · Jelani Nelson (UC Berkeley) · Tamas Sarlos (Google) · Moshe Shechner (Tel Aviv University) · Uri Stemmer (Tel Aviv University and Google Research)

Exploiting Independent Instruments: Identification and Distribution Generalization
Sorawit Saengkyongam (University of Copenhagen) · Leonard Henckel (Copenhagen University) · Niklas Pfister (University of Copenhagen) · Jonas Peters (University of Copenhagen)

UniREx: A Unified Learning Framework for Language Model Rationale Extraction
Aaron Chan (University of Southern California) · Maziar Sanjabi (Meta AI) · Lambert Mathias (Facebook) · Liang Tan (Facebook) · Shaoliang Nie (Facebook) · Xiaochang Peng () · Xiang Ren (University of Southern California) · Hamed Firooz (Facebook)

Greedy when Sure and Conservative when Uncertain about the Opponents
Haobo Fu (Tencent AI Lab) · Ye Tian (Tencent AI Lab) · Hongxiang Yu (SJTU) · Weiming Liu (University of Science and Technology of China) · Shuang Wu (Tencent) · Jiechao Xiong (Tencent AI Lab) · Ying Wen (Shanghai Jiao Tong University) · Kai Li (Institute of Automation, Chinese Academy of Sciences) · Junliang Xing (Tsinghua University) · Qiang Fu (Tencent AI Lab) · Wei Yang (Tencent AI Lab)

Efficient Contextual Bandits with CVaR Regret
Yinglun Zhu (University of Wisconsin-Madison) · Paul Mineiro (Microsoft)

Iterative Double Sketching for Faster Least-Squares Optimization
Rui Wang (Renmin University of China) · Yanyan Ouyang (Renmin University of China) · Wangli Xu (Renmin University of China)

Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path
Haoyuan Cai (Tsinghua University) · Tengyu Ma (Stanford) · Simon Du (University of Washington)

Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework
Jiahao Su (University of Maryland, College Park) · Wonmin Byeon (NVIDIA Research) · Furong Huang (University of Maryland)

Fat–Tailed Variational Inference with Anisotropic Tail Adaptive Flows
Feynman Liang (UC Berkeley) · Michael Mahoney (UC Berkeley) · Liam Hodgkinson (University of California Berkeley)

Estimating and Penalizing Induced Preference Shifts in Recommender Systems
Micah Carroll (UC Berkeley) · Dylan Hadfield-Menell (Massachusetts Institute of Technology) · Stuart Russell (UC Berkeley) · Anca Dragan (University of California, Berkeley)

Improving Self-Supervised Speech Representations by Disentangling Speakers
Kaizhi Qian (MIT-IBM Watson AI Lab) · Yang Zhang (MIT-IBM Watson AI Lab) · Heting Gao (University of Illinois at Urbana-Champaign) · Junrui Ni (University Of Illinois at Urbana-Champaign) · Cheng-I Lai (MIT) · David Cox (MIT-IBM Watson AI Lab) · Mark Hasegawa-Johnson (University of Illinois) · Shiyu Chang (UCSB)

Linear Bandit Algorithms with Sublinear Time Complexity
Shuo Yang (University of Texas at Austin) · Tongzheng Ren (UT Austin / Google Brain) · Sanjay Shakkottai (University of Texas at Austin) · Eric Price (UT-Austin) · Inderjit Dhillon (UT Austin & Amazon) · Sujay Sanghavi (UT Austin)

On the Role of Discount Factor in Offline Reinforcement Learning
Hao Hu (Tsinghua University) · yiqin yang (Tsinghua University) · Chongjie Zhang (Tsinghua University) · Qianchuan Zhao (Tsinghua University)

Deep Causal Metric Learning
Xiang Deng (State University of New York at Binghamton) · Zhongfei Zhang (Binghamton University)

Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
Jen-Hao Rick Chang (Apple) · Ashish Shrivastava (Apple) · Hema Koppula (Apple ) · Xiaoshuai Zhang (UC San Diego) · Oncel Tuzel (Apple)

NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields
Shanyan Guan (Shanghai Jiao Tong University) · Huayu Deng (Shanghai Jiao Tong University) · Yunbo Wang (Tsinghua University) · Xiaokang Yang (Shanghai Jiao Tong University of China)

Guaranteed Robust Deep Learning against Extreme Label Noise using Self-supervised Learning
Yihao Xue (UCLA) · Kyle Whitecross (UCLA) · Baharan Mirzasoleiman (Stanford University)

Model Selection in Batch Policy Optimization
Jonathan Lee (Stanford University) · George Tucker (Google Brain) · Ofir Nachum (Google Brain) · Bo Dai (Google Brain)

Active fairness auditing
Tom Yan (Carnegie Mellon University) · Chicheng Zhang (University of Arizona)

Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)
Yu Huang (Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University) · Junyang Lin (Alibaba Group) · Chang Zhou (Alibaba Group) · Hongxia Yang (Alibaba Group) · Longbo Huang (Tsinghua University)

Robust Group Synchronization via Quadratic Programming
Yunpeng Shi (University of Minnesota) · Cole Wyeth (University of Minnesota, Twin Cities) · Gilad Lerman (University of Minnesota)

How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models
Ahmed Alaa (UCLA) · Boris van Breugel (University of Cambridge) · Evgeny S. Saveliev (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

Efficiently Learning the Topology and Behavior of a Networked Dynamical System Via Active Queries
Daniel Rosenkrantz (University of Virginia) · Abhijin Adiga (Biocomplexity Institute & Initiative, Univ. of VA) · Madhav Marathe (Biocomplexity Institute & Initiative, University of Virginia) · Zirou Qiu (University of Virginia) · S. S. Ravi (University of Virginia and University at Albany -- SUNY) · Richard Stearns (University at Albany -- SUNY) · Anil Vullikanti (University of Virginia)

Memory-Based Model Editing at Scale
Eric Mitchell (Stanford) · Charles Lin (Stanford) · Antoine Bosselut (EPFL) · Christopher Manning (Stanford University) · Chelsea Finn (Stanford)

Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
Gautam Kamath (University of Waterloo) · Xingtu Liu (University of Waterloo) · Huanyu Zhang (Facebook)

On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis
Qi Lyu (Oregon State University) · Xiao Fu (Oregon State University)

On Measuring Causal Contributions via do-interventions
Yonghan Jung (Purdue University) · Shiva Kasiviswanathan (Amazon Research AI) · Jin Tian (Iowa State University) · Dominik Janzing (Amazon) · Patrick Bloebaum (Amazon AWS) · Elias Bareinboim (Columbia)

Deep equilibrium networks are sensitive to initialization statistics
Atish Agarwala (Google Research) · Samuel Schoenholz (Google Brain)

A General Recipe for Likelihood-free Bayesian Optimization
Jiaming Song (Stanford) · Lantao Yu (Stanford University) · Willie Neiswanger (Stanford University) · Stefano Ermon (Stanford University)

Position Prediction as an Effective Pretraining Strategy
Shuangfei Zhai (Apple) · Navdeep Jaitly (Apple) · Jason Ramapuram (Apple) · Dan Busbridge (Apple) · Tatiana Likhomanenko (Apple) · Joseph Cheng (Apple) · Walter Talbott (Apple) · Chen Huang (Apple Inc.) · Hanlin Goh (Apple) · Joshua M Susskind (Apple, Inc.)

Mitigating Neural Network Overconfidence with Logit Normalization
Hongxin Wei (Nanyang Technological University) · RENCHUNZI XIE (Nanyang Technological University) · Hao Cheng (Nanjing University) · LEI FENG (Nanyang Technological University) · Bo An (Nanyang Technological University) · Yixuan Li (University of Wisconsin-Madison)

Continual Learning via Function-Space Variational Inference
Tim Rudner (University of Oxford) · Freddie Bickford Smith (University of Oxford) · QIXUAN FENG (University of Oxford) · Yee-Whye Teh (Oxford and DeepMind) · Yarin Gal (University of Oxford)

Actor-Critic based Improper Reinforcement Learning
Mohammadi Zaki (Indian Institute of Science Bangalore) · Avi Mohan (Boston University) · Aditya Gopalan (Indian Institute of Science (IISc)) · Shie Mannor (Technion)

Understanding Instance-Level Impact of Fairness Constraints
Jialu Wang (University of California, Santa Cruz) · Xin Eric Wang (University of California, Santa Cruz) · Yang Liu (UC Santa Cruz)

Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning
Momin Abbas (Rensselaer Polytechnic Institute) · Quan Xiao (Rensselaer Polytechnic Institute) · Lisha Chen (Rensselaer Polytechnic Institute) · Pin-Yu Chen (IBM Research AI) · Tianyi Chen (Rensselaer Polytechnic Institute)

Partial disentanglement for domain adaptation
Lingjing Kong (Carnegie Mellon University) · Shaoan Xie (Carnegie Mellon University) · Weiran Yao (Carnegie Mellon University) · Yujia Zheng (Carnegie Mellon University) · Guangyi Chen (MBZUAI) · Petar Stojanov (Broad Institute of MIT and Harvard) · Victor Akinwande (Carnegie Mellon University) · Kun Zhang (Carnegie Mellon University)

Structured Stochastic Gradient MCMC
Antonios Alexos (University of California, Irvine) · Alex Boyd (University of California, Irvine) · Stephan Mandt (University of California, Irivine)

Validating Causal Inference Methods
Harsh Parikh (Duke University) · Carlos Varjao (Amazon.com) · Louise Xu (Amazon.com) · Eric Tchetgen Tchetgen (The Wharton School, University of Pennsylvania)

Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers
Rui Liu (University of Michigan, Ann Arbor) · Young Jin Kim (Microsoft) · Alexandre Muzio (Microsoft) · Barzan Mozafari (University of Michigan) · Hany Hassan (microsoft)

Communication-efficient Distributed Learning for Large Batch Optimization
Rui Liu (University of Michigan, Ann Arbor) · Barzan Mozafari (University of Michigan)

IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages
Emanuele Bugliarello (University of Copenhagen) · Fangyu Liu (University of Cambridge) · Jonas Pfeiffer (TU-Darmstadt) · Siva Reddy (Mila) · Desmond Elliott (University of Copenhagen) · Edoardo Maria Ponti (Mila Montreal / University of Cambridge) · Ivan Vulić (University of Cambridge)

Diffusion Models for Adversarial Purification
Weili Nie (NVIDIA) · Brandon Guo (Caltech) · Yujia Huang (California Institute of Technology) · Chaowei Xiao (University of Michigan) · Arash Vahdat (NVIDIA Research) · Animashree Anandkumar (Caltech and NVIDIA)

Proximal Exploration for Model-guided Protein Sequence Design
Zhizhou Ren (University of Illinois at Urbana-Champaign) · Jiahan Li (Peking University) · Fan Ding (Purdue University) · Yuan Zhou (UIUC) · Jianzhu Ma (Institute for Artificial Intelligence, Peking University) · Jian Peng (UIUC)

Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost
Dan Qiao (UCSB) · Ming Yin (UC Santa Barbara) · Ming Min (University of California, Santa Barbara) · Yu-Xiang Wang (UC Santa Barbara)

Optimal Algorithms for Mean Estimation under Local Differential Privacy
Hilal Asi (Stanford University) · Vitaly Feldman (Apple) · Kunal Talwar (Apple)

How to Fill the Optimal Set? Population Gradient Descent with Harmless Diversity
Chengyue Gong (UT Austin) · (None) · Qiang Liu (UT Austin)

Constants Matter: The Performance Gains of Active Learning
Stephen Mussmann (University of Washington) · Sanjoy Dasgupta (UCSD)

Sparse Invariant Risk Minimization
Xiao Zhou (HKUST) · Yong LIN (The Hong Kong University of Science and Technology) · Weizhong Zhang (The Hong Kong University of Science and Technology) · Tong Zhang (HKUST)

Efficient Variance Reduction for Meta-learning
Hansi Yang (The Hong Kong University of Science and Technology) · James Kwok (Hong Kong University of Science and Technology)

Training Your Sparse Neural Network Better with Any Mask
Ajay Jaiswal (The University of Texas at Austin) · Haoyu Ma (University of California, Irvine) · Tianlong Chen (University of Texas at Austin) · Ying Ding (University of Texas at Austin) · Zhangyang “Atlas” Wang (University of Texas at Austin)

Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling
Tung Nguyen (University of California, Los Angeles) · Aditya Grover (UCLA)

Identifiability Conditions for Domain Adaptation
Ishaan Gulrajani (Stanford) · Tatsunori Hashimoto (Stanford)

An Intriguing Property of Geophysics Inversion
Yinan Feng (Los Alamos National Laboratory) · Yinpeng Chen (Microsoft) · Shihang Feng (Los Alamos National Laboratory) · Peng Jin (The Pennsylvania State University) · Zicheng Liu (Microsoft) · Youzuo Lin (Los Alamos National Laboratory)

Order Constraints in Optimal Transport
Yu Chin Fabian Lim (IBM Research) · Laura Wynter (IBM Research) · Shiau Hong Lim (IBM Research)

Learning from a Learning User for Optimal Recommendations
Fan Yao (University of Virginia) · Chuanhao Li (University of Virginia) · Denis Nekipelov (University of Virginia) · Hongning Wang (University of Virginia) · Haifeng Xu (University of Virginia)

Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms
Xuchuang Wang (The Chinese University of Hong Kong) · Hong Xie (College of Computer Science, Chongqing University) · John C. S. Lui (The Chinese University of Hong Kong)

Federated Learning with Partial Model Personalization
Krishna Pillutla (University of Washington) · Kshitiz Malik (Facebook) · Abdel-rahman Mohamed (Facebook AI Research (FAIR)) · Michael Rabbat (Facebook) · Maziar Sanjabi (Meta AI) · Lin Xiao (Meta AI Research)

Inducing Causal Structure for Interpretable Neural Networks
Atticus Geiger (Stanford) · Zhengxuan Wu (Stanford University) · Hanson Lu (Stanford University) · Elisa Kreiss (Stanford University) · Thomas Icard (Stanford University) · Noah Goodman (Stanford University) · Christopher Potts (Stanford University) · Joshua Rozner (Stanford University)

Entropic Gromov-Wasserstein between Gaussian Distributions
Huy Nguyen (VinAI Research) · Khang Le (The University of Texas at Austin) · Dung Le (École Polytechnique) · (None) · Tung Pham (VINAI ARTIFICIAL INTELLIGENCE APPLICATION AND RESEARCH JOINT STOCK COMPANY) · Nhat Ho (University of Texas at Austin)

The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning
Wei-Ning Chen (Stanford University) · Christopher Choquette Choo (Google) · Peter Kairouz (Google) · Ananda Suresh (Google Research)

Optimally Controllable Perceptual Lossy Compression
Zeyu Yan (Shanghai Jiao Tong University) · Fei Wen (Shanghai Jiao Tong University) · Peilin Liu (Shanghai Jiao Tong University)

Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs
Meyer Scetbon (CREST, ENSAE) · Gabriel Peyré (CNRS and ENS) · Marco Cuturi (Google)

Planning with Diffusion for Flexible Behavior Synthesis
Michael Janner (UC Berkeley) · Yilun Du (MIT) · Josh Tenenbaum (MIT) · Sergey Levine (UC Berkeley)

Understanding Dataset Difficulty in NLP with $\mathcal{V}$-Usable Information
Kawin Ethayarajh (Stanford University) · Yejin Choi (University of Washington) · Swabha Swayamdipta (Allen Institute for AI)

COAT: Measuring Object Compositionality in Emergent Representations
Sirui Xie (UCLA) · Ari Morcos (Facebook AI Research (FAIR)) · Song-Chun Zhu (UCLA) · Shanmukha Ramakrishna Vedantam (Facebook AI Research)

Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
Jiatai Huang (Tsinghua University) · Yan Dai (Tsinghua University) · Longbo Huang (Tsinghua University)

Removing Batch Normalization Boosts Adversarial Training
Haotao Wang (University of Texas at Austin) · Aston Zhang (Amazon AI) · Shuai Zheng (Amazon Web Services) · Xingjian Shi (Amazon Web Services) · Mu Li () · Zhangyang “Atlas” Wang (University of Texas at Austin)

Generalized Beliefs for Cooperative AI
Darius Muglich (University of Oxford) · Luisa Zintgraf (University of Oxford) · Christian Schroeder de Witt (University of Oxford) · Shimon Whiteson (University of Oxford) · Jakob Foerster (Oxford university)

Secure Quantized Training for Deep Learning
Marcel Keller (CSIRO's Data61) · Ke Sun (CSIRO Data61 and ANU)

A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization
Songtao Lu (University of Minnesota Twin Cities)

Robust Training of Neural Networks using Scale Invariant Architectures
Zhiyuan Li (Princeton University) · Srinadh Bhojanapalli (Google AI) · Manzil Zaheer (Google Research) · Sashank Jakkam Reddi (Google) · Sanjiv Kumar (Google Research, NY)

No-Regret Learning in Time-Varying Zero-Sum Games
Mengxiao Zhang (University of Southern California) · Peng Zhao (Nanjing University) · Haipeng Luo (University of Southern California) · Zhi-Hua Zhou (Nanjing University)

DisPFL: Towards Communication-Efficient Personalized Federated learning via Decentralized Sparse Training
Rong Dai (University of Science and Technology of China) · Li Shen (JD Explore Academy) · Fengxiang He (JD.com Inc) · Xinmei Tian (University of Science and Technology of China) · Dacheng Tao ()

Bit Prioritization in Variational Autoencoders via Progressive Coding
Rui Shu (Stanford University) · Stefano Ermon (Stanford University)

Transfer Learning In Differential Privacy's Hybrid-Model
Or Sheffet (Bar Ilan University) · Refael Kohen (Bar-Ilan University)

Double Sampling Randomized Smoothing
Linyi Li (UIUC) · Jiawei Zhang (UIUC) · Tao Xie (Peking University) · Bo Li (UIUC)

Active Multi-Task Representation Learning
Yifang Chen (University of Washington) · Kevin Jamieson (University of Washington) · Simon Du (University of Washington)

TPC: Transformation-Specific Smoothing for Point Cloud Models
Wenda Chu (Tsinghua University) · Linyi Li (UIUC) · Bo Li (UIUC)

Region-Based Semantic Factorization in GANs
Jiapeng Zhu (The Hong Kong University of Science and Technology) · Yujun Shen (Ant Group) · Yinghao Xu (Chinese University of Hong Kong) · Deli Zhao (Alibaba Group) · Qifeng Chen (HKUST)

Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense
Guangyu Shen (Purdue University) · Yingqi Liu (Purdue University) · Guanhong Tao (Purdue University) · Qiuling Xu (Purdue University) · ZHUO ZHANG (Purdue University) · Shengwei An (Purdue University) · Shiqing Ma (Rutgers University) · Xiangyu Zhang (Purdue University)

Individual Preference Stability for Clustering
Saba Ahmadi (Toyota Technological Institute at Chicago) · Pranjal Awasthi (Google) · Samir Khuller (Northwestern University) · Matthäus Kleindessner (Amazon) · Jamie Morgenstern (U Washington) · Pattara Sukprasert (Northwestern University) · Ali Vakilian (Toyota Technological Institute at Chicago)

Learning to Estimate and Refine Fluid Motion with Physical Dynamics
Mingrui Zhang (Imperial College London) · Jianhong Wang (Imperial College London) · James Tlhomole (Imperial College London) · Matthew Piggott (Imperial College London)

Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score Matching
Cheng Lu (Tsinghua University) · Kaiwen Zheng (Tsinghua University) · Fan Bao (Tsinghua University) · Chongxuan Li (Tsinghua University) · Jianfei Chen (Tsinghua University) · Jun Zhu (Tsinghua University)

Sequential- and Parallel- Constrained Max-value Entropy Search via Information Lower Bound
Shion Takeno (Nagoya Institute of Technology) · Tomoyuki Tamura (Nagoya Institue of Technology / National Institute for Material Science) · Kazuki Shitara (Osaka University) · Masayuki Karasuyama (Nagoya Institute of Technology)

Path-Gradient Estimators for Continuous Normalizing Flows
Lorenz Vaitl (TU Berlin) · Kim A. Nicoli (TU Berlin) · Shinichi Nakajima (TU Berlin) · Pan Kessel (TU Berlin)

UniRank: Unimodal Bandit Algorithms for Online Ranking
Camille-Sovanneary GAUTHIER (Louis Vuitton) · Romaric Gaudel (Ensai, CREST) · Elisa Fromont (Université Rennes 1, IRISA/INRIA rba)

Efficient Representation Learning via Adaptive Context Pooling
Chen Huang (Apple Inc.) · Walter Talbott (Apple) · Navdeep Jaitly (Apple) · Joshua M Susskind (Apple, Inc.)

Demystifying the Adversarial Robustness of Random Transformation Defenses
Chawin Sitawarin (UC Berkeley) · Zachary Golan-Strieb (UC Berkeley) · David Wagner (UC Berkeley)

Active Sampling for Min-Max Fairness
Jacob Abernethy (Georgia Institute of Technology) · Pranjal Awasthi (Google) · Matthäus Kleindessner (Amazon) · Jamie Morgenstern (U Washington) · Chris Russell (Amazon) · Jie Zhang (University of Washington)

Let Invariant Rationale Discovery Inspire Graph Contrastive Learning
Sihang Li (University of Science and Technology of China) · Xiang Wang (School of Computing, National University of Singapore) · An Zhang (National University of Singapore) · Ying-Xin Wu (University of Science and Technology of China) · Xiangnan He (University of Science and Technology of China) · Tat-Seng Chua (National university of Singapore)

Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees
Verónica Álvarez (BCAM-Basque Center for Applied Mathematics) · Santiago Mazuelas (Basque Center for Applied Mathematics) · Jose A Lozano (UPV/EHU)

Scaling up Universal Methods for Convex Optimization
Kimon Antonakopoulos (EPFL) · Dong Quan Vu (Laboratoire d'informatique de Grenoble - LIG) · Volkan Cevher (EPFL) · Kfir Levy (-) · Panayotis Mertikopoulos (CNRS and Criteo AI Lab)

Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four
Stephan Wäldchen (TU Berlin) · Sebastian Pokutta (ZIB/TUB) · Felix Huber (ZIB)

Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning
Wei Fu (Tsinghua University) · Chao Yu (Tsinghua University) · Zelai Xu (Tsinghua University) · Jiaqi Yang (University of California, Berkeley) · Yi Wu (UC Berkeley)

Making Linear MDPs Practical via Contrastive Representation Learning
Tianjun Zhang (UC Berkeley) · Tongzheng Ren (UT Austin / Google Brain) · Mengjiao Yang (Google Brain) · Joseph E Gonzalez (UC Berkeley) · Dale Schuurmans (Google / University of Alberta) · Bo Dai (Google Brain)

Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations
Nabeel Seedat (University of Cambridge) · Fergus Imrie (University of California, Los Angeles) · Alexis Bellot (University of Cambridge) · Zhaozhi Qian (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails
Shaojie Li (Renmin University of China) · Yong Liu (Renmin University of China)

Marginal Tail-Adaptive Normalizing Flows
Mike Laszkiewicz (Ruhr University Bochum) · Johannes Lederer (Ruhr-University Bochum) · Asja Fischer (Ruhr University Bochum)

Data-SUITE: Data-centric identification of in-distribution incongruous examples
Nabeel Seedat (University of Cambridge) · Jonathan Crabbé (University of Cambridge) · Mihaela van der Schaar (University of Cambridge and UCLA)

Lie Point Symmetry Data Augmentation for Neural PDE Solvers
Daniel Worrall (DeepMind) · Johannes Brandstetter (Microsoft Research) · Max Welling (University of Amsterdam)

A random matrix analysis of online learning: coping with limited memory resources
Hugo Lebeau (Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP, LIG, 38000 Grenoble, France) · Romain Couillet (Univ. Grenoble Alpes, CNRS, Inria, Grenoble INP, LIG, 38000 Grenoble, France) · Florent Chatelain (Univ. Grenoble Alpes)

Revisiting Online Submodular Minimization: Gap-Dependent Regret Bounds, Best of Both Worlds and Adversarial Robustness
Shinji Ito (NEC Corporation)

Score-Guided Intermediate Level Optimization: Fast Langevin Mixing for Inverse Problems
Giannis Daras (The University of Texas at Austin) · Yuval Dagan (MIT) · Alexandros Dimakis (UT Austin) · Constantinos Daskalakis (MIT)

Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
Matthias Weissenbacher (RIKEN Center for Advanced Intelligence Project (AIP)) · Samrath Sinha (University of Toronto) · Animesh Garg (University of Toronto, Vector Institute, Nvidia) · Yoshinobu Kawahara (Kyushu University / RIKEN)

Score matching enables causal discovery of nonlinear additive noise models
Paul Rolland (Ecole Polytechnique Fédérale de Lausanne) · Volkan Cevher (EPFL) · Matthäus Kleindessner (Amazon) · Chris Russell (Amazon) · Dominik Janzing (Amazon Research Tübingen) · Bernhard Schölkopf (Amazon / MPI Intelligent Systems) · Francesco Locatello (Amazon Lablet)

Function-space Inference with Sparse Implicit Processes
Simon R Santana (Institute of Mathematical Sciences ICMAT-CSIC) · Bryan Zaldivar (IFIC) · Daniel Hernandez-Lobato (Universidad Autonoma de Madrid)

Input Dependent Sparse Gaussian Processes
Bahram Jafrasteh (Biomedical Research and Innovation Institute of Cádiz (INiBICA)) · Carlos Villacampa-Calvo (Universidad Autónoma de Madrid) · Daniel Hernandez-Lobato (Universidad Autonoma de Madrid)

Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications
Alexandre Capone (TUM) · Armin Lederer (Technical University of Munich) · Sandra Hirche (Technical University of Munich)

Tackling covariate shift with node-based Bayesian neural networks
Trung Trinh (Aalto University) · Markus Heinonen (Aalto University) · Luigi Acerbi (University of Helsinki) · Samuel Kaski (Aalto University and University of Manchester)

Versatile Dueling Bandits: Best-of-both World Analyses for Learning from Relative Preferences
Aadirupa Saha (Microsoft Research) · Pierre Gaillard (INRIA)

Sample Efficient Learning of Predictors that Complement Humans
Mohammad-Amin Charusaie (Max-Planck-Institute for Intelligent Systems) · Hussein Mozannar (Massachusetts Institute of Technology) · David Sontag (Massachusetts Institute of Technology) · Samira Samadi (MPI-IS)

Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning
Haoqi Yuan (Peking University) · Zongqing Lu (Peking University)

LyaNet: A Lyapunov Framework for Training Neural ODEs
Ivan Dario Jimenez Rodriguez (California Institute of Technology) · Aaron Ames (Caltech) · Yisong Yue (Caltech)

Analysis of Stochastic Processes through Replay Buffers
Shirli Di-Castro Shashua (Technion) · Shie Mannor (Technion) · Dotan Di Castro (Yahoo Research)

A Reduction from contextual bandits to estimations
Jiahao He (The Hong Kong University of Science and Technology) · Jiheng Zhang (HKUST) · Rachel Zhang (HKUST)

Overcoming Oscillations in Quantization-Aware Training
Markus Nagel (Qualcomm AI Research) · Marios Fournarakis (Qualcomm AI Research) · Yelysei Bondarenko (Qualcomm AI Research) · Tijmen Blankevoort (Qualcomm)

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
Vihang Patil (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) · Markus Hofmarcher (ELLIS Unit Linz, Johannes Kepler University Linz) · Marius-Constantin Dinu (LIT AI Lab / University Linz) · Matthias Dorfer (enliteAI) · Patrick Blies (EnliteAI GmbH) · Johannes Brandstetter (Microsoft Research) · Jose A. Arjona-Medina (Dynatrace Research) · Sepp Hochreiter (ELLIS Unit Linz, LIT AI Lab, Institute for Machine Learning, Johannes Kepler University, Institute for Advanced Research in Artificial Intelligence (IARAI))

Objective Robustness in Deep Reinforcement Learning
Jack Koch (Unaffiliated) · Lauro Langosco di Langosco (ETH) · Jacob Pfau (University of Edinburgh) · David Krueger (University of Cambridge) · Lee Sharkey (University of Tuebingen)

Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation
Sebastian Lee (Imperial College / UCL) · Stefano Sarao Mannelli (University College London) · Claudia Clopath (Imperial College London) · Sebastian Goldt (International School of Advanced Studies (SISSA)) · Andrew Saxe (UCL)

Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems
Miguel Suau (Delft University of Technology) · Jinke He (Delft University of Technology) · Matthijs T. J. Spaan (Delft University of Technology) · Frans Oliehoek (Delft University of Technology)

A Closer Look at Smoothness in Domain Adversarial Training
Harsh Rangwani (Indian Institute of Science) · Sumukh K Aithal (PES University) · Mayank Mishra (Indian Institute of Science) · Arihant Jain (Indian Institute of Science) · Venkatesh Babu Radhakrishnan (Indian Institute of Science)

Robust Imitation Learning against Variations in Environment Dynamics
Jongseong Chae (KAIST) · Seungyul Han (UNIST) · Whiyoung Jung (KAIST) · MYUNG-SIK CHO (KAIST) · Sungho Choi (Korea Advanced Institute of Science and Technology (KAIST)) · Youngchul Sung (KAIST)

A Dynamical System Perspective for Lipschitz Neural Networks
Laurent Meunier (Dauphine University - FAIR Paris) · Blaise Delattre (Université Paris-Dauphine) · Alexandre ARAUJO (INRIA) · Alexandre Allauzen (LAMSADE, Paris-Dauphine University)

An initial alignment between neural network and target is needed for gradient descent to learn
Emmanuel Abbe (EPFL) · Elisabetta Cornacchia (EPFL) · Jan Hazla (EPFL) · Christopher Marquis (EPFL)

Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation
Xiaoyu Chen (Peking University) · Han Zhong (Peking University) · Zhuoran Yang (Yale University) · Zhaoran Wang (Northwestern University) · Liwei Wang (Peking University)

Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning
Giorgio Manganini (Gran Sasso Science Institute) · Angelo Damiani (Gran Sasso Science Institute) · Alberto Maria Metelli (Politecnico di Milano) · Marcello Restelli (Politecnico di Milano)

Personalized Federated Learning through Local Memorization
Othmane MARFOQ (Inria / Accenture) · Giovanni Neglia (Inria) · Richard Vidal (Accenture) · Laetitia Kameni (Accenture)

Modeling Adversarial Noise for Adversarial Training
Dawei Zhou (Xidian University) · Nannan Wang (Xidian University) · Bo Han (HKBU / RIKEN) · Tongliang Liu (The University of Sydney)

Meta-Learning Hypothesis Spaces for Sequential Decision-making
Parnian Kassraie (ETH Zurich) · Jonas Rothfuss (ETH) · Andreas Krause (ETH Zurich)

Ripple Attention for Visual Perception with Sub-quadratic Complexity
Lin Zheng (The University of Hong Kong) · Huijie Pan (The University of Hongkong) · Lingpeng Kong (The University of Hong Kong)

Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
Han Zhong (Peking University) · Wei Xiong (The Hong Kong University of Science and Technology) · Jiyuan Tan (Fudan University) · Liwei Wang (Peking University) · Tong Zhang (HKUST) · Zhaoran Wang (Northwestern University) · Zhuoran Yang (Yale University)

An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guarantees
Guillaume Braun (Inria) · Hemant Tyagi (Inria Lille - Nord Europe) · Christophe Biernacki (Inria)

A Difference Standardization Method for Mutual Transfer Learning
Haoqing Xu (Southeast University) · Meng Wang (Southeast University) · Beilun Wang (Southeast University)

Improving Adversarial Robustness via Mutual Information Estimation
Dawei Zhou (Xidian University) · Nannan Wang (Xidian University) · Xinbo Gao (Chongqing University of Posts and Telecommunications) · Bo Han (HKBU / RIKEN) · Xiaoyu Wang (-) · Yibing Zhan (Jingdong ) · Tongliang Liu (The University of Sydney)

Predict and Optimize: Through the Lens of Learning to Rank
Jayanta Mandi (Vrije Universiteit Brussel) · Víctor Bucarey (Universidad de O'Higgins) · Maxime Mulamba Ke Tchomba (Vrije Universiteit Brussel) · Tias Guns (KU Leuven)

Unsupervised Image Representation Learning with Deep Latent Particles
Tal Daniel (Technion) · Aviv Tamar (Technion)

Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Angelos Filos (University of Oxford) · Eszter Vértes (DeepMind) · Zita Marinho (DeepMind) · Gregory Farquhar (DeepMind) · Diana Borsa (DeepMind) · Abe Friesen (DeepMind) · Feryal Behbahani (DeepMind) · Tom Schaul (DeepMind) · Andre Barreto (DeepMind) · Simon Osindero (DeepMind)

Improving Transformers with Probabilistic Attention Keys
Tam Nguyen (FPT Software Company Limited, FPT Cau Giay building, Duy Tan street, Dich Vong Hau ward, Cau Giay district, Hanoi) · Tan Nguyen (University of California, Los Angeles) · Dung Le (College of Engineering and Computer Science, VinUniversity) · Duy Khuong Nguyen (FPT Software Company Limited) · Viet-Anh Tran (Deezer) · Richard Baraniuk (OpenStax / Rice University) · Nhat Ho (University of Texas at Austin) · Stanley Osher (UCLA)

PAC-Bayes Bounds for Meta-Learning
Arezou Rezazadeh (Chalmers University of Technology)

Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings
Jan Macdonald (Technische Universität Berlin) · Mathieu Besançon (Zuse Institute Berlin) · Sebastian Pokutta (ZIB/TUB)

Differentiable Top-k Classification Learning
Felix Petersen (University of Konstanz) · Hilde Kuehne (University of Frankfurt) · Christian Borgelt (University of Salzburg) · Oliver Deussen (University of Konstanz)

The Teaching Dimension of Regularized Kernel Learners
Hong Qian (East China Normal University) · Xu-Hui Liu (Nanjing University) · Chen-Xi Su (East China Normal University) · Aimin Zhou (East China Normal University) · Yang Yu (Nanjing University)

Equivariant Quantum Graph Circuits
Peter Mernyei (Charm Therapeutics) · Konstantinos Meichanetzidis (Cambridge Quantum Computing) · Ismail Ceylan (University of Oxford)

Robust SDE-based variational formulations for solving linear PDEs via deep learning
Lorenz Richter (dida, Zuse Institute Berlin, Freie Universität Berlin) · Julius Berner (University of Vienna)

A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1
Adil Salim (Microsoft) · Lukang Sun (KAUST) · Peter Richtarik (KAUST)

On The Generalization Analysis of Adversarial Learning
Waleed Mustafa (TU Kaiserslautern) · Yunwen Lei (University of Birmingham) · Marius Kloft (TU Kaiserslautern)

Measuring Representational Robustness of Neural Networks Through Shared Invariances
Vedant Nanda (University of Maryland, College Park) · Till Speicher (MPI-SWS) · Camila Kolling (PUCRS) · John P Dickerson (Arthur AI & Univ. of Maryland) · Krishna Gummadi (MPI-SWS) · Adrian Weller (University of Cambridge, Alan Turing Institute)

Label-Descriptive Patterns and Their Application to Characterizing Classification Errors
Michael Hedderich (Saarland University, Saarland Informatics Campus) · Jonas Fischer (Max Planck Institute for Informatics) · Dietrich Klakow (Saarland University) · Jilles Vreeken (CISPA Helmholtz Center for Information Security)

Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems
Manuel Brenner (Central Institute for Mental Health Mannheim) · Florian Hess (Central Institute of Mental Health Mannheim) · Jonas M Mikhaeil (Heidelberg University) · Leonard Bereska (University of Amsterdam) · Zahra Monfared (CIMH/ Heidelberg University) · Po-Chen Kuo (University of Washington) · Daniel Durstewitz (CIMH/ Heidelberg University)

Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization
Mariia Seleznova (Ludwig Maximilian University of Munich) · Gitta Kutyniok (Ludwig Maximilian University of Munich)

History Compression via Language Models in Reinforcement Learning
Fabian Paischer (Johannes Kepler University Linz) · Thomas Adler (LIT AI Lab / JKU Linz) · Vihang Patil (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria) · Angela Bitto-Nemling (JKU) · Markus Holzleitner (LIT AI Lab / University Linz) · Sebastian Lehner (JKU Linz) · Hamid Eghbal-zadeh (LIT AI Lab, Johannes Kepler University) · Sepp Hochreiter (ELLIS Unit Linz, LIT AI Lab, Institute for Machine Learning, Johannes Kepler University, Institute for Advanced Research in Artificial Intelligence (IARAI))

A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving
Luca Carminati (Politecnico di Milano) · Federico Cacciamani (Politecnico di Milano) · Marco Ciccone (Politecnico di Milano) · Nicola Gatti (Politecnico di Milano)

Subspace Learning for Effective Meta-Learning
Weisen Jiang (Hong Kong University of Science and Technology) · James Kwok (Hong Kong University of Science and Technology) · Yu Zhang (Hong Kong University of Science and Technology)

Equivariance versus Augmentation for Spherical Images
Jan Gerken (Technical University of Berlin) · Oscar Carlsson (Chalmers University of Technology) · Hampus Linander (University of Gothenburg) · Fredrik Ohlsson (Umea University) · Christoffer Petersson (Chalmers) · Daniel Persson (Chalmers University of Technology)

Learning Pseudometric-based Action Representations for Offline Reinforcement Learning
Pengjie Gu (Nanyang Technological University) · Mengchen Zhao (Huawei Noah's Ark Lab) · Chen Chen (Huawei Noah’s Ark Lab) · Dong Li (Huawei Noah's Ark Lab) · Jianye Hao (Huawei Noah's Ark Lab) · Bo An (Nanyang Technological University)

Importance Weighted Kernel Bayes' Rule
Liyuan Xu (Gatsby Computational Neuralscience Unit) · Yutian Chen (DeepMind) · Arnaud Doucet (Google DeepMind) · Arthur Gretton (Gatsby Computational Neuroscience Unit)

Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxation
Adarsh Barik (Purdue University) · Jean Honorio (Purdue University)

Utilizing Expert Features for Contrastive Learning of Time-Series Representations
Manuel Nonnenmacher (Bosch Center for Artificial Intelligence) · Lukas Oldenburg (Bosch Center for Artificial Intelligence (BCAI)) · Ingo Steinwart (University of Stuttgart) · David Reeb (Bosch Center for Artificial Intelligence)

Generalised Policy Improvement with Geometric Policy Composition
Shantanu Thakoor (DeepMind) · Mark Rowland (DeepMind) · Diana Borsa (DeepMind) · Will Dabney (DeepMind) · Remi Munos (DeepMind) · Andre Barreto (DeepMind)

A Modern Self-Referential Weight Matrix That Learns to Modify Itself
Kazuki Irie (The Swiss AI Lab IDSIA, University of Lugano) · Imanol Schlag (IDSIA) · Robert Cordas (IDSIA) · Jürgen Schmidhuber (Swiss AI Lab)

Graph-Coupled Oscillator Networks
T. Konstantin Rusch (ETH Zurich) · Ben Chamberlain (Twitter) · James Rowbottom (Twitter) · Siddhartha Mishra (ETH Zurich) · Michael Bronstein (Twitter)

Adapting k-means Algorithms for Outliers
Christoph Grunau (ETH Zürich) · Vaclav Rozhon (ETH)

The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention
Kazuki Irie (The Swiss AI Lab IDSIA, University of Lugano) · Robert Cordas (IDSIA) · Jürgen Schmidhuber (Swiss AI Lab)

Easy Variational Inference for Categorical Models via an Independent Binary Approximation
Michael Wojnowicz (Tufts University) · Shuchin Aeron (Tufts University) · Eric Miller (Tufts University) · Michael Hughes (Tufts University)

Calibrated Learning to Defer with One-vs-All Classifiers
Rajeev Verma (University of Amsterdam) · Eric Nalisnick (University of Amsterdam)

Reconstructing nonlinear dynamical systems from multi-modal time series
Daniel Kramer (Central Institute of Mental Health) · Philine Bommer (TU Berlin) · Daniel Durstewitz (CIMH/ Heidelberg University) · (None) · Georgia Koppe (Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University)

Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
Boxiang Lyu (University of Chicago Booth School of Business) · Zhaoran Wang (Northwestern University) · Mladen Kolar (University of Chicago Booth School of Business) · Zhuoran Yang (Yale University)

Fisher SAM: Information Geometry and Sharpness Aware Minimisation
Minyoung Kim (Samsung AI Center) · Da Li (Samsung) · Xu Hu (Ecole des Ponts ParisTech) · Timothy Hospedales (Samsung AI Centre / University of Edinburgh)

Sparser Kernel Herding with Pairwise Conditional Gradients without Swap Steps
Kazuma Tsuji (MUFG Bank) · Ken'ichiro Tanaka (The University of Tokyo) · Sebastian Pokutta (ZIB/TUB)

From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses
Daniil Tiapkin (HSE University) · Denis Belomestny (Universitaet Duisburg-Essen) · Eric Moulines (Ecole Polytechnique) · Alexey Naumov (National Research University Higher School of Economics) · Sergey Samsonov (National Research University Higher School of Economics) · Yunhao Tang (DeepMind) · Michal Valko (DeepMind / Inria / ENS Paris-Saclay) · Pierre MENARD (OvGU)

PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs
Zehao Dong (Washington University in St. Louis) · Muhan Zhang (Peking University) · Fuhai Li (Washington University in St Louis) · Yixin Chen (Washington University in St. Louis)

On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games
Robert Loftin (TU Delft) · Frans Oliehoek (Delft University of Technology)

Fast Population-Based Reinforcement Learning on a Single Machine
Arthur Flajolet (InstaDeep) · Claire Bizon Monroc (InstaDeep, Inria, DI ENS PSL) · Karim Beguir (InstaDeep) · Thomas Pierrot (InstaDeep)

Delay-adaptive step-sizes for asynchronous learning
Xuyang Wu (KTH Royal Institute of Technology) · Sindri Magnusson (Stockholm University) · Hamid Reza Feyzmahdavian (ABB) · Mikael Johansson (KTH Royal Institute of Technology)

Learning fair representation with a parametric integral probability metric
Dongha Kim (Sungshin Women's University) · Kunwoong Kim (Seoul National University) · Insung Kong (Seoul National University) · Ilsang Ohn (Inha University) · Yongdai Kim (Seoul National University)

Rethinking Attention-Model Explainability through Faithfulness Violation Test
Yibing Liu (City University of Hong Kong) · Haoliang Li (CityU) · Yangyang Guo (National University of Singapore) · Chenqi KONG (City Unversity of Hong Kong) · Jing Li (The Hong Kong Polytechnic University) · Shiqi Wang (City University of Hong Kong)

Antibody-Antigen Interface Design via Hierarchical Structure Refinement
Wengong Jin (MIT) · Regina Barzilay (MIT CSAIL) · Tommi Jaakkola (MIT)

Prompting Decision Transformer for Few-shot Policy Generalization
Mengdi Xu (Carnegie Mellon University) · Yikang Shen (University of Montreal) · Shun Zhang (MIT-IBM Watson AI Lab) · Yuchen Lu (Mila & University of Montreal) · Ding Zhao (Carnegie Mellon University) · Josh Tenenbaum (MIT) · Chuang Gan (MIT-IBM Watson AI Lab)

Active Nearest Neighbor Regression Through Delaunay Refinement
Alexander Kravberg (KTH - Royal Institute of Technology) · Giovanni Luca Marchetti (KTH Royal Institute of Technology) · Vladislav Polianskii (KTH Royal Institute of Technology) · Anastasiia Varava (-) · Florian T. Pokorny (KTH Royal Institute of Technology) · Danica Kragic (KTH)

Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
Francesco Croce (University of Tuebingen) · Sven Gowal (DeepMind) · Thomas Brunner (Technical University of Munich) · Evan Shelhamer (DeepMind) · Matthias Hein (University of Tübingen) · Taylan Cemgil (DeepMind)

Learning Augmented Binary Search Trees
Honghao Lin (Carnegie Mellon University) · Tian Luo (Carnegie Mellon University) · David Woodruff (Carnegie Mellon University)

Variational Inference for Infinitely Deep Neural Networks
Achille Nazaret (Columbia University) · David Blei (Columbia University)

Additive Gaussian Processes Revisited
Xiaoyu Lu (Amazon) · Alexis Boukouvalas (Amazon) · James Hensman (PROWLER.io)

SPECTRE : Spectral Conditioning Overcomes the Expressivity Limits of One-shot Graph Generators
Karolis Martinkus (ETH Zurich) · Andreas Loukas (EPFL) · Nathanaël Perraudin (Swiss Data Science Center, ETH Zürich) · Roger Wattenhofer (ETH Zurich)

The Pathway Race Reduction: Dynamics of Abstraction in Gated Networks
Andrew Saxe (UCL) · Shagun Sodhani (Facebook AI Research) · Sam Lewallen (University College London)

On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces
Amrit Singh Bedi (University of Maryland, College Park) · Souradip Chakraborty (University of Maryland, College Park) · Anjaly Parayil (Microsoft) · Brian Sadler (US Army Research Lab) · Pratap Tokekar (University of Maryland) · Alec Koppel (JP Morgan Chase AI Research)

Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors
Geert-Jan Huizing (ENS PSL) · Laura Cantini (Ecole Normale Supérieure) · Gabriel Peyré (CNRS and ENS)

Generalizing to New Physical Systems via Context-Informed Dynamics Model
Matthieu Kirchmeyer (Sorbonne Université & Criteo AI Lab) · Yuan Yin (Sorbonne Université, ISIR, MLIA team) · Jérémie DONA (Sorbonne Université) · Nicolas Baskiotis (LIP6) · alain rakotomamonjy (Criteo) · Patrick Gallinari (Sorbonne Universite, Criteo AI Lab)

Deep Probability Estimation
Sheng Liu (NYU) · Aakash Kaku (New York University) · Weicheng Zhu (New York University) · Matan Leibovich (New York University) · Sreyas Mohan (NYU) · Boyang Yu (NYU Center for Data Science) · Haoxiang Huang (New York University) · Laure Zanna (NYU) · Narges Razavian (New York University) · Jonathan Niles-Weed (NYU) · Carlos Fernandez-Granda ()

Continual Repeated Annealed Flow Transport Monte Carlo
Alexander Matthews (DeepMind) · Michael Arbel (Inria Grenoble Rhône Alpes) · Danilo J. Rezende (DeepMind) · Arnaud Doucet (Google DeepMind)

A Regret Minimization Approach to Multi-Agent Control
Udaya Ghai (Princeton) · Udari Madhuhshani (Princeton University) · Naomi Leonard (Princeton University) · Elad Hazan (Princeton University and Google Brain)

Locally Sparse Neural Networks for Tabular Biomedical Data
Junchen Yang (Yale University) · Ofir Lindenbaum (Bar-Ilan University) · Yuval Kluger (Yale School of Medicine)

Provable Acceleration of Heavy Ball beyond Quadratics for a class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out
Jun-Kun Wang (Yale University) · Chi-Heng Lin (Georgia Institute of Technology) · Andre Wibisono (Yale University) · Bin Hu (University of Illinois at Urbana-Champaign)

Efficient Approximate Inference for Stationary Kernel on Frequency domain
Yohan Jung (KAIST) · Kyungwoo Song (University of Seoul) · Jinkyoo Park (KAIST)

Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder
Tiexin QIN (City University of Hong Kong) · Shiqi Wang (City University of Hong Kong) · Haoliang Li (CityU)

Variational Inference with Locally Enhanced Bounds for Hierarchical Models
Tomas Geffner (UMass Amherst) · Justin Domke (University of Massachusetts, Amherst)

Latent Outlier Exposure for Anomaly Detection with Contaminated Data
Chen Qiu (Bosch Center for AI/TU Kaiserslautern) · Aodong Li (University of California, Irvine) · Marius Kloft (TU Kaiserslautern) · Maja Rudolph (BCAI) · Stephan Mandt (University of California, Irivine)

Priyatham Kattakinda (University of Maryland) · Soheil Feizi (University of Maryland)

A Framework for Learning to Request Rich and Contextually Useful Information from Humans
Khanh Nguyen (University of Maryland) · Yonatan Bisk (Carnegie Mellon University) · Hal Daumé III (Microsoft Research / University of Maryland)

Adaptive Conformal Predictions for Time Series
Margaux Zaffran (INRIA) · Aymeric Dieuleveut (École polytechnique) · Olivier FERON (EDF) · Yannig Goude (EDF Lab Paris-Saclay) · julie Josse (Polytechnique/INRIA)

Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
Pier Giuseppe Sessa (ETH Zürich) · Maryam Kamgarpour (EPFL) · Andreas Krause (ETH Zurich)

Proximal denoiser for convergent plug-and-play optimization with nonconvex regularization
Samuel Hurault (Université de Bordeaux) · Nicolas Papadakis (CNRS/IMB) · Arthur Leclaire (Institut Mathématiques de Bordeaux)

Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models
(None) · Tommaso Salvatori (University of Oxford) · Yuhang Song (University of Oxford) · Thomas Lukasiewicz (TU Wien and University of Oxford) · Rafal Bogacz (University of Oxford)

Generating Distributional Adversarial Examples to Evade Statistical Detectors
Yigitcan Kaya (University of Maryland, College Park) · Muhammad Bilal Zafar (Amazon Web Services) · Sergul Aydore (Amazon) · Nathalie Rauschmayr (Amazon Web Services) · Krishnaram Kenthapadi (Fiddler AI)

Achieving Minimax Rates in Pool-Based Batch Active Learning
Zhilei Wang (Citadel Securities) · Claudio Gentile (Google Research) · Tong Zhang (Google)

Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes
Conor Tillinghast (Recursion) · Zheng Wang (University of Utah) · Shandian Zhe (University of Utah)

MetAug: Contrastive Learning via Meta Feature Augmentation
Jiangmeng Li (Institute of Software Chinese Academy of Sciences) · Wenwen Qiang (Institute of software Chinese academy of sciences) · Changwen Zheng (Institute of Software, Chinese Academy of Sciences) · Bing Su (Institute of Software, Chinese Academy of Sciences) · Hui Xiong (the State University of New Jersey)

Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic Models
Elvis Nava (ETH Zurich) · John Zhang (MIT) · Mike Yan Michelis (ETH Zürich) · Tao Du (MIT) · Pingchuan Ma (MIT CSAIL) · Benjamin F. Grewe (ETH Zurich) · Wojciech Matusik (MIT) · Robert Katzschmann (ETH Zurich)

Principal Component Flows
Edmond Cunningham (University of Massachusetts Amherst) · Adam Cobb (SRI International) · Susmit Jha (SRI International)

Self-conditioning Pre-Trained Language Models
Xavier Suau (Apple) · Luca Zappella (Apple) · Nicholas Apostoloff (Apple Inc.)

Tractable Uncertainty for Structure Learning
Benjie Wang (University of Oxford) · Matthew Wicker (University of Oxford) · Marta Kwiatkowska (Oxford University)

Robust Counterfactual Explanations for Tree-Based Ensembles
Sanghamitra Dutta (JP Morgan AI Research) · Jason Long (J P Morgan) · Saumitra Mishra (JP Morgan) · Cecilia Tilli (J.P. Morgan AI Research) · Daniele Magazzeni (JP Morgan)

Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning
Yunhao Tang (DeepMind)

Efficient low rank convex bounds for pairwise discrete Graphical Model
Valentin Durante (ANITI, INRAE) · Thomas Schiex (INRAE) · George Katsirelos (INRAE)

Improve Single-Point Zeroth-Order Optimization Using High-Pass and Low-Pass Filters
Xin Chen (Harvard University) · Yujie Tang (Harvard University) · Na Li (Harvard University)

Invariant Ancestry Search
Phillip Bredahl Mogensen (University of Copenhagen) · Nikolaj Thams (University of Copenhagen) · Jonas Peters (University of Copenhagen)

Exact Learning of Preference Structure: Single-peaked Preferences and Beyond
Sonja Kraiczy (Oxford University) · Edith Elkind (University of Oxford)

Rich Feature Construction for the Optimization-Generalization Dilemma
Jianyu Zhang (New York University) · David Lopez-Paz (Facebook AI Research) · Léon Bottou (Meta AI)

Augment with Care: Contrastive Learning for Combinatorial Problems
Haonan Duan (University of Toronto) · Pashootan Vaezipoor (University of Toronto and Vector Institute) · Max Paulus (ETH Zurich) · Yangjun Ruan (University of Toronto) · Chris Maddison (University of Toronto)

LSB: Local Self-Balancing MCMC in Discrete Spaces

A data-driven approach for learning to control computers
Peter Humphreys (Deepmind) · David Raposo (DeepMind) · Tobias Pohlen (DeepMind) · Gregory Thornton (Deepmind) · Rachita Chhaparia (Deepmind) · Alistair Muldal (DeepMind) · Josh Abramson (DeepMind) · Petko Georgiev (Deepmind) · Adam Santoro (DeepMind) · Timothy Lillicrap (Google DeepMind)

DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks
Zhuang Wang (Rice University) · Zhaozhuo Xu (Rice University) · Xinyu Wu (Rice University) · Anshumali Shrivastava (Rice University) · T. S. Eugene Ng (Rice University)

Disentangling Disease-related Representation from Obscure for Disease Prediction
Chu-ran Wang (Center for Data Science, Peking University) · Fei Gao (Peking University) · Fandong Zhang (Deepwise AI Lab) · Fangwei Zhong (Peking University) · Yizhou Yu (The University of Hong Kong) · Yizhou Wang (Peking University)

Learning Multiscale Transformer Models for Sequence Generation
Bei Li (Northeastern University, China) · Tong Zheng (Northeastern University) · yi jing (Northeastern University) · Chengbo Jiao (University of Electronic Science and Technology of China) · Tong Xiao (Northeastern University) · Jingbo Zhu (Northeastern University, China)

Nyström Kernel Mean Embeddings
Antoine Chatalic (MaLGa and DIBRIS, Università di Genova (Italy)) · Nicolas Schreuder (MALGA, DIBRIS, Università di Genova) · Lorenzo Rosasco (unige, mit, iit) · Alessandro Rudi (INRIA, École Normale Supérieure)

Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Fabrizio Pittorino (Bocconi University) · Antonio Ferraro (Bocconi University) · Gabriele Perugini (Bocconi University) · Christoph Feinauer (Bocconi University) · Carlo Baldassi (Bocconi University) · RIccardo Zecchina (Bocconi University)

LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation
David Ireland (University of Warwick) · Giovanni Montana (University of Warwick)

Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
Junwen Bai (Cornell) · Shufeng Kong (Cornell University) · Carla Gomes (Cornell University)

Private Adaptive Optimization with Side information
Tian Li (Carnegie Mellon University) · Manzil Zaheer (Google Research) · Sashank Jakkam Reddi (Google) · Virginia Smith (Carnegie Mellon University)

Improving Screening Processes via Calibrated Subset Selection
Luke Lequn Wang (Cornell University) · Thorsten Joachims (Cornell) · Manuel Gomez-Rodriguez (MPI-SWS)

Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology
Valentin Hofmann (University of Oxford, LMU Munich) · Janet Pierrehumbert (University of Oxford) · Hinrich Schütze (Ludwig-Maximilians-Universität München)

Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning
Hidetaka Kamigaito (Nara Institute of Science and Technology) · Katsuhiko Hayashi (Hokkaido University)

Fairness Interventions as (Dis)Incentives for Strategic Manipulation
Xueru Zhang (Ohio State University) · Mohammadmahdi Khaliligarekani (None) · Kun Jin (University of Michigan, Ann Arbor) · Parinaz Naghizadeh (Ohio State University) · Mingyan Liu (University of Michigan, Ann Arbor)

Smoothed Adversarial Linear Contextual Bandits with Knapsacks
Vidyashankar Sivakumar (Amazon) · Shiliang Zuo (University of Illinois Urbana-Champaign) · Arindam Banerjee (UIUC)

Context-Aware Drift Detection
Oliver Cobb (Seldon Technologies) · Arnaud Van Looveren (Seldon Technologies)

Fast Relative Entropy Coding with A* coding
Gergely Flamich (University of Cambridge) · Stratis Markou (University of Cambridge) · Jose Miguel Hernandez-Lobato (University of Cambridge)

Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints
Martino Bernasconi (Politecnico di Milano) · Federico Cacciamani (Politecnico di Milano) · Matteo Castiglioni (Politecnico di Milano) · Alberto Marchesi (Politecnico di Milano) · Nicola Gatti (Politecnico di Milano) · Francesco Trovò (Politecnico di Milano)

Markov Chain Monte Carlo for Continuous-Time Switching Dynamical Systems
Lukas Köhs (Technische Universität Darmstadt) · Bastian Alt (Technische Universität Darmstadt) · Heinz Koeppl (TU Darmstadt)

A Theoretical Comparison of Graph Neural Network Extensions
Pál András Papp (Huawei Technologies) · Roger Wattenhofer (ETH Zurich)

Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions
Heiner Kremer (MPI for Intelligent Systems, Tübingen) · Jia-Jie Zhu (Weierstrass Institute, Berlin) · Krikamol Muandet (Max Planck Institute for Intelligent Systems) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Differentially Private Maximal Information Coefficients
John Lazarsfeld (Yale University) · Aaron Johnson (U.S. Naval Research Laboratory) · Emmanuel Adeniran (Yale University)

Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert
Yoonhyung Lee (Kakao Entertainment Corp.) · Sungdong Lee (Seoul National University) · Joong-Ho (Johann) Won (Seoul National University)

A Study on the Ramanujan Graph Property of Winning Lottery Tickets
Bithika Pal (Indian Institute of Technology Kharagpur) · Arindam Biswas (University of Copenhagen ) · Sudeshna Kolay (Indian Institute of Technology Kharagpur) · Pabitra Mitra (Indian Institute of Technology Kharagpur) · Biswajit Basu (Trinity College Dublin)

Selective Regression under Fairness Criteria
Abhin Shah (MIT) · Yuheng Bu (MIT) · Joshua Lee (Massachusetts Institute of Technology) · Prasanna Sattigeri (IBM Research) · Rameswar Panda (MIT-IBM Watson AI Lab, IBM Research) · Subhro Das (MIT-IBM Watson AI Lab, IBM Research) · Gregory Wornell (MIT)

Hindering Adversarial Attacks with Implicit Neural Representations
Andrei A Rusu (DeepMind) · Dan Andrei Calian (DeepMind) · Sven Gowal (DeepMind) · Raia Hadsell (DeepMind)

Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing
Mohammad Zalbagi Darestani (Rice University) · Jiayu Liu (Technical University of Munich) · Reinhard Heckel (Technical University of Munich and Rice University)

How to Stay Curious while avoiding Noisy TVs using Aleatoric Uncertainty Estimation
Augustine Mavor-Parker (University College London) · Kimberly Young (University College London) · Caswell Barry (University College London) · Lewis Griffin (University College London)

Causal Inference Through the Structural Causal Marginal Problem
Luigi Gresele (MPI for Intelligent Systems, Tübingen) · Julius von Kügelgen (MPI for Intelligent Systems, Tübingen & University of Cambridge) · Jonas Kübler (Max Planck Institute for Intelligent Systems, Tübingen) · Elke Kirschbaum (Amazon Web Services) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany) · Dominik Janzing (Amazon)

A Simple Reward-free Approach to Constrained Reinforcement Learning
Sobhan Miryoosefi (Princeton University) · Chi Jin (Princeton University)

Self-supervised learning with random-projection quantizer for speech recognition
Chung-Cheng Chiu (Google Brain) · James Qin (Google) · Yu Zhang (Google) · Jiahui Yu (Google) · Yonghui Wu (Google)

Understanding Contrastive Learning Requires Incorporating Inductive Biases
Nikunj Umesh Saunshi (Princeton University) · Jordan Ash (Microsoft Research) · Surbhi Goel (Microsoft Research) · Dipendra Kumar Misra (Microsoft Research) · Cyril Zhang (Microsoft Research) · Sanjeev Arora (Princeton University) · Sham Kakade (Harvard University) · Akshay Krishnamurthy (Microsoft Research)

Sampling from wide Bayesian neural networks
Jiri Hron (University of Cambridge) · Roman Novak (Google Brain) · Jeffrey Pennington (Google Brain) · Jascha Sohl-Dickstein (Google Brain)

Multiclass learning with margin: exponential rates with no bias-variance trade-off
Stefano Vigogna (University of Rome Tor Vergata) · Giacomo Meanti (University of Genoa) · Ernesto De Vito (Dima, Università di Genova) · Lorenzo Rosasco (unige, mit, iit)

Adversarial Vulnerability of Randomized Ensembles
Hassan Dbouk (University of Illinois at Urbana-Champaign) · Naresh Shanbhag (University of Illinois)

Adversarially Trained Actor Critic for Offline Reinforcement Learning
Ching-An Cheng (Microsoft Research) · Tengyang Xie (University of Illinois at Urbana-Champaign) · Nan Jiang (University of Illinois at Urbana-Champaign) · Alekh Agarwal (Microsoft Research)

Efficient Learning of CNNs using Patch Based Features
Alon Brutzkus (Tel Aviv University) · Amir Globerson (Tel Aviv University, Google) · Eran Malach (Hebrew University Jerusalem Israel) · Alon Regev Netser (The Hebrew University of Jerusalem) · Shai Shalev-Shwartz ()

Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence
Dongsheng Ding (University of Southern California) · Chen-Yu Wei (University of Southern California) · Mihailo Jovanovic (University of Southern California) · Kaiqing Zhang (MIT)

RUMs from Head-to-Head Contests
Matteo Almanza (Sapienza University) · Flavio Chierichetti (Sapienza University) · Ravi Kumar (Google) · Alessandro Panconesi (Sapienza, University of Rome) · Andrew Tomkins (Google)

Shuffle Private Linear Contextual Bandits
Sayak Ray Chowdhury (Indian Institute of Science) · Xingyu Zhou (Wayne State University)

The Geometry of Robust Value Functions
Kaixin Wang (National University of Singapore) · Navdeep Kumar (Technion, Israel Institute of Technology) · Kuangqi Zhou (National University of Singapore) · Bryan Hooi (NUS) · Jiashi Feng (ByteDance) · Shie Mannor (Technion)

StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models
Adam Liska (DeepMind) · Tomas Kocisky (DeepMind) · Elena Gribovskaya (DeepMind) · Tayfun Terzi (DeepMind) · Eren Sezener (DeepMind) · Devang Agrawal (DeepMind) · Cyprien de Masson d'Autume (DeepMind) · Tim Scholtes (DeepMind) · Manzil Zaheer (Google Research) · Susannah Young (DeepMind) · Ellen Gilsenan-McMahon (DeepMind) · Sophia Austin (DeepMind) · Phil Blunsom (DeepMind and Oxford University) · Angeliki Lazaridou (DeepMind)

Do More Negative Samples Necessarily Hurt In Contrastive Learning?
Pranjal Awasthi (Google) · Nishanth Dikkala (Google Research) · Pritish Kamath (Google Research)

Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction
Zijian Liu (Boston University) · Ta Duy Nguyen (Boston University) · Alina Ene (Boston University) · Huy Nguyen (Northeastern University)

The Transfo-k-mer: protein fitness prediction with auto-regressive transformers and inference-time retrieval
Pascal Notin (University of Oxford) · Mafalda Dias (Havard Medical School) · Jonathan Frazer (Harvard University) · Javier Marchena Hurtado (Harvard Medical School) · Aidan Gomez (Oxford) · Debora Marks (Harvard Medical School) · Yarin Gal (University of Oxford)

Particle Transformer for Jet Tagging
Huilin Qu (CERN) · Congqiao Li (Peking University) · Sitian Qian (Peking University)

pathGCN: Learning General Graph Spatial Operators from Paths
Moshe Eliasof (Ben-Gurion University of the Negev) · Eldad Haber (University of British Columbia) · Eran Treister (Ben-Gurion University of the Negev)

The State of Sparse Training in Deep Reinforcement Learning
Laura Graesser (Google) · Utku Evci (Google) · Erich Elsen (Google) · Pablo Samuel Castro (Google Brain)

Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters
Vladislav Kurenkov (Tinkoff) · Sergey Kolesnikov (Tinkoff)

Certifying Out-of-Domain Generalization for Blackbox Functions
Maurice Weber (ETH Zurich) · Linyi Li (UIUC) · (None) · Bo Li (UIUC) · Ce Zhang (ETH Zurich)

Towards Understanding Convergence of Simultaneous Gradient Descent-Ascent in Minimax Optimization
Haochuan Li (MIT) · Farzan Farnia (The Chinese University of Hong Kong) · Subhro Das (MIT-IBM Watson AI Lab, IBM Research) · Ali Jadbabaie (Massachusetts Institute of Technology)

Minimizing Control for Credit Assignment with Strong Feedback
Alexander Meulemans (Institute of Neuroinformatics | University of Zurich | ETH Zurich) · Maria Cervera (ETH Zurich) · Matilde Tristany Farinha (ETH Zurich) · João Sacramento (ETH Zurich) · Benjamin F. Grewe (ETH Zurich)

FEDNEST: Federated Bilevel Optimization
Davoud Ataee Tarzanagh (University of Michigan) · Mingchen Li (University of California, Riverside) · Christos Thrampoulidis (University of British Columbia) · Samet Oymak (University of California, Riverside)

Sanity Simulations for Saliency Methods
Joon Kim (Carnegie Mellon University) · Gregory Plumb (Carnegie Mellon University) · Ameet Talwalkar (Carnegie Mellon University)

VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty
Randy Ardywibowo (Texas A&M University) · Zepeng Huo (Texas A&M University) · Zhangyang “Atlas” Wang (University of Texas at Austin) · Bobak Mortazavi (Texas A&M University) · Shuai Huang (University of Washington) · Xiaoning Qian (Texas A&M University)

Differentially Private Community Detection for Stochastic Block Models
Mohamed Mohamed (Princeton University) · Dung Nguyen (University of Virginia) · Anil Vullikanti (Biocomplexity Institute and Dept of Computer Science, University of Virginia) · Ravi Tandon (University of Arizona)

Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers
Francesco Croce (University of Tuebingen) · Matthias Hein (University of Tübingen)

Finite-Sum Coupled Compositional Stochastic Optimization: Theories and Applications
Bokun Wang (The University of Iowa) · Tianbao Yang (The University of Iowa)

Constrained Discrete Black-Box Optimization using Mixed-Integer Programming
Theodore Papalexopoulos (Massachusetts Institute of Technology) · Christian Tjandraatmadja (Google) · Ross Anderson (Google Research) · Juan Pablo Vielma (Google and MIT) · David Belanger (Google)

Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
Tianlong Chen (University of Texas at Austin) · Zhenyu Zhang (University of Science and Technology of China) · Sijia Liu (Michigan State University) · Yang Zhang (MIT-IBM Watson AI Lab) · Shiyu Chang (UCSB) · Zhangyang “Atlas” Wang (University of Texas at Austin)

SpaceMAP: Visualizing High-Dimensional Data by Space Expansion
Xinrui Zu (Delft University of Technology) · Qian Tao (Delft University of Technology)

Linearity Grafting: How Neuron Pruning Helps Certifiable Robustness
Tianlong Chen (University of Texas at Austin) · Huan Zhang (CMU) · Zhenyu Zhang (University of Science and Technology of China) · Shiyu Chang (UCSB) · Sijia Liu (Michigan State University) · Pin-Yu Chen (IBM Research AI) · Zhangyang “Atlas” Wang (University of Texas at Austin)

Online Learning for Min Sum Set Cover and Pandora’s Box
Evangelia Gergatsouli (UW-Madison) · Christos Tzamos (UW-Madison)

Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes
Hongyi Guo (Northwestern University) · Qi Cai (Northwestern University) · Yufeng Zhang (Northwestern University) · Zhuoran Yang (Yale University) · Zhaoran Wang (Northwestern University)

Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning
Aviv Netanyahu (MIT) · Tianmin Shu (MIT) · Josh Tenenbaum (MIT) · Pulkit Agrawal (MIT)

The CLRS Algorithmic Reasoning Benchmark
Petar Veličković (DeepMind / University of Cambridge) · Adrià Puigdomenech Badia (Deepmind) · David Budden (DeepMind) · Razvan Pascanu (DeepMind) · Andrea Banino (DeepMind) · Misha Dashevskiy (DeepMind) · Raia Hadsell (DeepMind) · Charles Blundell (DeepMind)

Bayesian Model Selection, the Marginal Likelihood, and Generalization
Sanae Lotfi (New York University) · Pavel Izmailov (New York University) · Gregory Benton (New York University) · Micah Goldblum (New York University) · Andrew Wilson (New York University)

SpeqNets: Sparsity-aware permutation-equivariant graph networks
Christopher Morris (RWTH Aachen) · Sandra Kiefer (RWTH Aachen University) · Gaurav Rattan (RWTH Aachen, Germany) · Siamak Ravanbakhsh (McGill - Mila)

Efficient First-Order Bayesian Optimization via Structured Automatic Differentiation
Sebastian Ament (Cornell University) · Carla Gomes (Cornell University)

A Tighter Analysis of Spectral Clustering, and Beyond
Peter Macgregor (University of Edinburgh) · He Sun (University of Edinburgh)

Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes
Gregory Benton (New York University) · Wesley Maddox (New York University) · Andrew Wilson (New York University)

Nested Exponential Weights and the Red Bus / Blue Bus Paradox
Matthieu Martin (Criteo AI Lab) · Panayotis Mertikopoulos (CNRS and Criteo AI Lab) · Thibaud J Rahier (INRIA) · Houssam Zenati (Criteo, INRIA)

Mitigating Gender Bias in Face Recognition using the von Mises-Fisher Mixture Model
Jean-Rémy Conti (Télécom Paris Idemia) · Nathan NOIRY (Telecom Paris) · Vincent Despiegel (Idemia) · Stéphane Gentric (IDEMIA) · Stephan Clemencon (Telecom ParisTech)

Anticorrelated Noise Injection for Improved Generalization
Antonio Orvieto (ETH Zurich) · Hans Kersting (ENS / INRIA) · Frank Proske (University of Oslo) · Francis Bach (INRIA - Ecole Normale Supérieure) · Aurelien Lucchi (ETH Zurich)

How Tempering Fixes Data Augmentation in Bayesian Neural Networks
Lorenzo Noci (ETH Zürich) · Gregor Bachmann (ETH Zurich) · Thomas Hofmann (ETH Zurich)

Massively Parallel $k$-Means Clustering for Perturbation Resilient Instances
Vincent Cohen-Addad (Google) · Vahab Mirrokni (Google Research) · Peilin Zhong (Google Research)

Resilient and Communication Efficient Learning for Heterogeneous Federated Systems
Zhuangdi Zhu (Michigan State University) · Junyuan Hong (Michigan State University) · Steve Drew (University of Calgary) · Jiayu Zhou (Michigan State University)

Scalable Computation of Causal Bounds
Madhumitha Shridharan (Columbia University) · Garud Iyengar (Columbia)

Improved Regret for Differentially Private Exploration in Linear MDP
Dung Ngo (University of Minnesota) · Giuseppe Vietri (University of Minnesota) · Steven Wu (Carnegie Mellon University)

Risk-Averse No-Regret Learning in Online Convex Games
Zifan Wang (Royal Institute of Technology) · Yi Shen (Duke University) · Michael Zavlanos (Duke University)

Describing Differences between Text Distributions with Natural Language
Ruiqi Zhong (UC Berkeley) · Charlie Snell (UC Berkeley) · Dan Klein (UC Berkeley) · Jacob Steinhardt (UC Berkeley)

Feature selection using e-values
Subhabrata Majumdar (Splunk) · Snigdhansu Chatterjee (University of Minnesota)

RECAPP: Crafting a More Efficient Catalyst for Convex Optimization
Yair Carmon (Tel Aviv University) · Arun Jambulapati (Stanford) · Yujia Jin (Stanford University) · Aaron Sidford (Stanford)

Direct Behavior Specification via Constrained Reinforcement Learning
Julien Roy (Mila) · Roger Girgis (Mila - Quebec AI Institute) · Joshua Romoff (Ubisoft) · Pierre-Luc Bacon (Mila) · Christopher Pal (MILA)

Architecture Agnostic Federated Learning for Neural Networks
Disha Makhija (University of Texas at Austin) · Xing Han (The University of Texas at Austin) · Nhat Ho (University of Texas at Austin) · Joydeep Ghosh (The University of Texas at Austin)

What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?
Colin Raffel (Google Brain) · Adam Roberts (Google Brain) · Hyung Won Chung (Google) · Iz Beltagy (Allen Institute for AI (AI2)) · Daniel Hesslow (Lighton) · Julien Launay (École Normale Supérieure) · Thomas Wang (Hugging Face) · Teven Le Scao (Hugging Face)

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
Yonggan Fu (Rice University) · Haichuan Yang (Facebook) · Jiayi Yuan (Rice University) · Meng Li (Facebook Inc) · Cheng Wan (Rice University) · Raghuraman Krishnamoorthi (Facebook) · Vikas Chandra (Facebook) · Yingyan Lin (Rice University)

No-Regret Learning in Partially-Informed Auctions
Wenshuo Guo (University of California, Berkeley) · Michael Jordan (UC Berkeley) · Ellen Vitercik (University of California, Berkeley)

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Mitchell Wortsman (University of Washington) · Gabriel Ilharco (University of Washington) · Samir Gadre (Columbia University) · Rebecca Roelofs (Google Research) · Raphael Gontijo Lopes (Google Brain) · Ari Morcos (Facebook AI Research (FAIR)) · Hongseok Namkoong (Columbia University) · Ali Farhadi (University of Washington, Allen Institue for AI) · Yair Carmon (Tel Aviv University) · Simon Kornblith (Google Brain) · Ludwig Schmidt (Toyota Research Institute)

Generalization and Robustness Implications in Object-Centric Learning
Andrea Dittadi (Technical University of Denmark) · Samuele Papa (University of Amsterdam) · Michele De Vita (DTU) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany) · Ole Winther (DTU and KU) · Francesco Locatello (Amazon Lablet)

Simultaneous Graph Signal Clustering and Graph Learning
Abdullah Karaaslanli (Michigan State University) · Selin Aviyente (Michigan State University)

Biological Sequence Design with GFlowNets
Moksh Jain (MILA / University of Montreal) · Emmanuel Bengio (McGill University) · Alex Hernandez-Garcia (Mila - Quebec AI Institute) · Jarrid Rector-Brooks (Mila, Universite de Montreal) · Bonaventure Dossou (Mila) · Chanakya Ekbote (Mila) · Jie Fu (Mila, University of Montreal) · Tianyu Zhang (Mila) · Michael Kilgour (New York University) · Dinghuai Zhang (Mila, Meta) · Lena Simine (McGill University) · Payel Das (IBM Research AI) · Yoshua Bengio (Mila - Quebec AI Institute)

Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times
Daniele Calandriello (DeepMind) · Luigi Carratino (University of Genoa) · Alessandro Lazaric (Facebook AI Research) · Michal Valko (DeepMind / Inria / ENS Paris-Saclay) · Lorenzo Rosasco (unige, mit, iit)

End-to-End Balancing for Causal Continuous Treatment-Effect Estimation
Mohammad Taha Bahadori (Amazon) · Eric Tchetgen Tchetgen (The Wharton School, University of Pennsylvania) · David Heckerman (Amazon)

Extended Unconstrained Features Model for Exploring Deep Neural Collapse
Tom Tirer (New York University) · Joan Bruna (New York University)

Deduplicating Training Data Mitigates Privacy Risks
Nikhil Kandpal (University of North Carolina, Chapel Hill) · Eric Wallace (U.C. Berkeley) · Colin Raffel (Google Brain)

Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm
Lechao Xiao (Google Research) · Jeffrey Pennington (Google Brain)

The Multivariate Community Hawkes Model for Dependent Relational Events in Continuous-time Networks
Hadeel Soliman (University of Toledo) · Lingfei Zhao (OSU) · Zhipeng Huang (The University of Toledo) · Subhadeep Paul (The Ohio State University) · Kevin Xu (University of Toledo)

Robust Models Are More Interpretable Because Attributions Look Normal
Zifan Wang (Carnegie Mellon University) · Matt Fredrikson (Carnegie Mellon University) · Anupam Datta (Carnegie Mellon University)

Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification
Camille Garcin (Université de Montpellier) · Maximilien Servajean (LIRMM - UPVM) · Alexis Joly (INRIA, FR) · Joseph Salmon (Université de Montpellier)

Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
Tianlong Chen (University of Texas at Austin) · Xuxi Chen (University of Texas at Austin) · Xiaolong Ma (Northeastern University) · Yanzhi Wang (Northeastern University) · Zhangyang “Atlas” Wang (University of Texas at Austin)

TACTiS: Transformer-Attentional Copulas for Time Series
Alexandre Drouin (ServiceNow / Université Laval) · Étienne Marcotte (ServiceNow Research) · Nicolas Chapados (Element AI (ServiceNow) & Imagia)

data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
Alexei Baevski (Foundational AI Research (Meta)) · Wei-Ning Hsu (Massachusetts Institute of Technology) · Qiantong Xu (Sambanova Systems) · Arun Babu () · Jiatao Gu (Facebook AI Research) · Michael Auli (Meta AI)

Proving Theorems using Incremental Learning and Hindsight Experience Replay
Eser Aygün (DeepMind) · Laurent Orseau (DeepMind) · Ankit Anand (DeepMind) · Xavier Glorot (DeepMind) · Stephen McAleer (CMU) · Vlad Firoiu (DeepMind) · Lei Zhang (DeepMind) · Doina Precup (DeepMind) · Shibl Mourad (DeepMind)

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization
Alberto Bietti (NYU) · Chen-Yu Wei (University of Southern California) · Miro Dudik (Microsoft Research) · John Langford (Microsoft Research) · Steven Wu (Carnegie Mellon University)

FITNESS: (Fine Tune on New and Similar Samples) to detect anomalies in streams with drift and outliers
Abishek Sankararaman (Amazon Web Services) · Vikramank Singh (Amazon) · Zhao Song (Amazon) · Balakrishnan Narayanaswamy (Amazon)

When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee
Dixian Zhu (University of Iowa) · Gang Li (the University of Iowa) · Bokun Wang (The University of Iowa) · Xiaodong Wu (University of Iowa) · Tianbao Yang (The University of Iowa)

PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
Matilde Gargiani (ETHZ) · Andrea Zanelli (zanellia@ethz.ch) · Andrea Martinelli (ETH Zurich) · Tyler Summers (University of Texas at Dallas) · John Lygeros (ETH Zürich)

Utility Theory for Markovian Sequential Decision Making
Mehran Shakerinava (McGill - Mila) · Siamak Ravanbakhsh (McGill - Mila)

Neural Tangent Kernel Empowered Federated Learning
Kai Yue (North Carolina State University) · Richeng Jin (NC State University) · Ryan Pilgrim (Independent Scholar) · Chau-Wai Wong (NC State University) · Dror Baron (NC State University) · Huaiyu Dai (NC State University)

Forward Operator Estimation in Generative Models with Kernel Transfer Operators
Zhichun Huang (Carnegie Mellon University) · Rudrasis Chakraborty (Butlr) · Vikas Singh (University of Wisconsin Madison)

Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks
Litian Liang (UC Irvine) · Yaosheng Xu (UC Irvine) · Stephen Mcaleer (UC Irvine) · Dailin Hu (UC Irvine) · Alexander Ihler (UC Irvine) · Pieter Abbeel (UC Berkeley & Covariant) · Roy Fox (UCI)

Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent
Ilias Diakonikolas (University of Wisconsin-Madison) · Vasilis Kontonis (University of Wisconsin Madison) · Christos Tzamos (UW-Madison) · Nikos Zarifis (UW-Madison)

Batched Dueling Bandits
Arpit Agarwal (Columbia University) · Rohan Ghuge (University of Michigan) · viswanath nagarajan (Univ Michigan, Ann Arbor)

ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks
Haoran You (Rice University) · Baopu Li (Baidu ) · Shi Huihong (Shihuihong) · Yonggan Fu (Rice University) · Yingyan Lin (Rice University)

Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time
David Woodruff (Carnegie Mellon University) · Amir Zandieh (MPI-INF)

Fast Finite Width Neural Tangent Kernel
Roman Novak (Google Brain) · Jascha Sohl-Dickstein (Google Brain) · Samuel Schoenholz (Google Brain)

Reparametrisation Gradient and Convergent SGD for Non-Differentiable Models via Smoothing: A Programming Language Approach
Dominik Wagner (University of Oxford) · Basim Khajwal (University of Oxford) · Luke Ong (University of Oxford)

Decentralized Online Convex Optimization in Networked Systems
Yiheng Lin (California Institute of Technology) · Judy Gan (Columbia University) · Guannan Qu (Carnegie Mellon University) · Yash Kanoria (Columbia Business School) · Adam Wierman (Caltech)

Implicit Bias of the Step Size in Linear Diagonal Neural Networks
Mor Shpigel Nacson (Technion) · Kavya Ravichandran (Toyota Technological Institute at Chicago) · Nati Srebro (Toyota Technological Institute at Chicago) · Daniel Soudry (Technion)

TURF: Two-Factor, Universal, Robust, Fast Distribution Learning Algorithm
Yi Hao (UCSD) · Ayush Jain (UC San Diego) · Alon Orlitsky (UCSD) · Vaishakh Ravindrakumar (UC San Diego)

An Analytical Update Rule for General Policy Optimization
Hepeng Li (University of Rhode Island) · Nicholas Clavette (University of Rhode Island) · Haibo He (University of Rhode Island)

A Differential Entropy Estimator for Training Neural Networks
Georg Pichler (TU Wien) · Pierre Colombo (IBM) · Malik Boudiaf (ETS Montreal) · Günther Koliander (Austrian Academy of Sciences) · Pablo Piantanida (CentraleSupelec, Université de Montréal)

BAMDT: Bayesian Additive Partial Multivariate Decision Trees for Nonparametric Regression
Zhao Tang Luo (Texas A&M University) · Huiyan Sang (Texas A&M University) · Bani Mallick (Texas A&M University)

Variational Sparse Coding with Learned Thresholding
Kion Fallah (Georgia Tech) · Christopher Rozell (Georgia Institute of Technology)

Robust Policy Learning over Multiple Uncertainty Sets
Annie Xie (Stanford University) · Shagun Sodhani (Facebook AI Research) · Chelsea Finn (Stanford) · Joelle Pineau (Facebook) · Amy Zhang (FAIR / UC Berkeley)

Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows
Michael Puthawala (Rice) · Matti Lassas (University of Helsinki) · Ivan Dokmanic (University of Basel / UIUC) · Maarten de Hoop (Rice University)

The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks
Xin Yu (University of Utah) · Thiago Serra (Carnegie Mellon University) · Srikumar Ramalingam (University of Utah) · Shandian Zhe (University of Utah)

Bayesian Imitation Learning for End-to-End Mobile Manipulation
Yuqing Du (UC Berkeley) · Daniel Ho (X, The Moonshot Factory) · Alexander Alemi (Google) · Eric Jang (Google Inc.) · Mohi Khansari (X, The Moonshot Factory)

RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests
Victor Chernozhukov (MIT) · Whitney Newey (MIT) · Víctor Quintas-Martínez (MIT) · Vasilis Syrgkanis (Microsoft Research)

How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
Mantas Mazeika (UIUC) · Bo Li (UIUC) · David Forsyth (Univeristy of Illinois at Urbana-Champaign)

Streaming Algorithms for Support-Aware Histograms
Justin Chen (MIT) · Piotr Indyk (MIT) · Tal Wagner (MIT)

Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk
Tianrui Chen (Boston University) · Aditya Gangrade (Carnegie Mellon University) · Venkatesh Saligrama (Boston University)

Prioritized training on points that are learnable, worth learning, and not yet learned
Sören Mindermann (University of Oxford) · Muhammed Razzak (University of Oxford) · Jan Brauner (University of Oxford) · Mrinank Sharma (University of Oxford) · Andreas Kirsch (University of Oxford) · Winnie Xu (University of Toronto) · Benedikt Höltgen (University of Oxford) · Aidan Gomez (Google) · Adrien Morisot (Cohere) · Sebastian Farquhar (University of Oxford) · Yarin Gal (University of Oxford)

Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations
Michael Zhang (Stanford University) · Nimit Sohoni (Stanford University) · Hongyang Zhang (Northeastern University) · Chelsea Finn (Stanford) · Christopher Re (Stanford University)

When Are Linear Stochastic Bandits Attackable?
Huazheng Wang (Princeton University) · Haifeng Xu (University of Virginia) · Hongning Wang (University of Virginia)

Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data
Timothy Castiglia (Rensselaer Polytechnic Institute) · Anirban Das (Rensselaer Polytechnic Institute) · Shiqiang Wang (IBM Research) · Stacy Patterson (Rensselaer Polytechnic Institute)

Low-Precision Stochastic Gradient Langevin Dynamics
Ruqi Zhang (UT Austin/Purdue) · Andrew Wilson (New York University) · Christopher De Sa (Cornell)

A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning
Archit Sharma (Stanford University) · Rehaan Ahmad (Stanford) · Chelsea Finn (Stanford)

Short-Term Plasticity Neurons Learning to Learn and Forget
Hector Garcia Rodriguez (Huawei Technologies - Zurich Research Center) · Qinghai Guo (ACS Lab, Huawei Technologies) · Timoleon Moraitis (Huawei Technologies - Zurich Research Center)

Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis
Ziyi Chen (University of Utah) · Yi Zhou (University of Utah) · Rong-Rong Chen (University of Utah) · Shaofeng Zou (University at Buffalo, the State University of New York)

A Langevin-like Sampler for Discrete Distributions
Ruqi Zhang (UT Austin/Purdue) · Xingchao Liu (University of Texas at Austin) · Qiang Liu (UT Austin)

Algorithms and Lower Bounds for Ridge Regression
Praneeth Kacham (Carnegie Mellon University) · David Woodruff (Carnegie Mellon University)

Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework
Ching-Yun (Irene) Ko (MIT) · Jeet Mohapatra (MIT) · Sijia Liu (Michigan State University) · Pin-Yu Chen (IBM Research AI) · Luca Daniel (Massachusetts Institute of Technology) · Lily Weng (UCSD)

Practical Almost-Linear-Time Approximation Algorithms for Hybrid and Overlapping Graph Clustering
Lorenzo Orecchia (University of Chicago) · Konstantinos Ameranis (University of Chicago) · Charalampos Tsourakakis (ISI Foundation, Boston University) · Kunal Talwar (Apple)

RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval
Yihan Wu (University of Pittsburgh) · Hongyang Zhang (University of Waterloo) · Heng Huang (University of Pittsburgh & JD Finance America Corporation)

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
Hannes Stärk (Massachusetts Institute of Technology) · Octavian Ganea (MIT) · Lagnajit Pattanaik (Massachusetts Institute of Technology) · Regina Barzilay (MIT CSAIL) · Tommi Jaakkola (MIT)

Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models
Viktor Bengs (University of Munich) · Aadirupa Saha (Microsoft Research) · Eyke Hüllermeier (Paderborn University)

Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
Yue Gao (University of Wisconsin at Madison) · Ilia Shumailov (University of Cambridge) · Kassem Fawaz (University of Wisconsin-Madison)

Improving and Assessing Anomaly Detectors for Large-Scale Settings
Dan Hendrycks (UC Berkeley) · Steven Basart (University of Chicago) · Mantas Mazeika (UIUC) · Andy Zou (UC Berkeley) · joseph kwon (Yale University) · Mohammadreza Mostajabi (Zendar) · Jacob Steinhardt (UC Berkeley)

SPDY: Accurate Pruning with Speedup Guarantees
Elias Frantar (IST Austria) · Dan Alistarh (IST Austria & NeuralMagic)

Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing Runtime
Kyriakos Axiotis (MIT) · (None)

Staged Training for Transformer Language Models
Sheng Shen (University of California, Berkeley) · Pete Walsh (Allen Institute of AI) · Kurt Keutzer (UC Berkeley) · Jesse Dodge (University of Washington) · Matthew Peters (AI2) · Iz Beltagy (Allen Institute for AI (AI2))

Do Differentiable Simulators Give Better Gradients for Policy Optimization?
Hyung Ju Suh (MIT) · Max Simchowitz (MIT) · Kaiqing Zhang (MIT) · Russ Tedrake (MIT)

Unifying Approximate Gradient Updates for Policy Optimization
Ramki Gummadi (Google Brain) · Junfeng Wen (Layer6 AI) · Saurabh Kumar (Google Brain) · Dale Schuurmans (Google / University of Alberta)

GraphFM: Improving Large-Scale GNN Training via Feature Momentum
Haiyang Yu (Texas A&M University) · Limei Wang (Texas A&M University) · Bokun Wang (The University of Iowa) · Meng Liu (Texas A&M University) · Tianbao Yang (The University of Iowa) · Shuiwang Ji (Texas A&M University)

Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing
Jiayin Jin (Auburn University) · Zeru Zhang (Auburn University) · Yang Zhou (Auburn University) · Lingfei Wu (JD.COM Silicon Valley Research Center)

Agnostic Learnability of Halfspaces via Logistic Loss
Ziwei Ji (Google Research) · Kwangjun Ahn (MIT EECS) · Pranjal Awasthi (Google) · Satyen Kale (Google Research) · Stefani Karp (Google/CMU)

Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding
Yifan Peng (Carnegie Mellon University) · Siddharth Dalmia (Carnegie Mellon University) · Ian Lane (Carnegie Mellon University) · Shinji Watanabe (Carnegie Mellon University)

Neural Inverse Kinematic
Raphael Bensadoun (Tel Aviv University) · Shir Gur (Tel Aviv University) · Nitsan Blau (Mentee Robotics) · Lior Wolf (Facebook AI Research and Tel Aviv University)

Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer
Lucas N. Alegre (Federal University of Rio Grande do Sul) · Ana Lucia Cetertich Bazzan (Universidade Federal do Rio Grande do Sul ) · Bruno C. da Silva (University of Massachusetts)

Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Javier Antorán (University of Cambridge) · David Janz (University of Cambridge) · James Allingham (University of Cambridge) · Erik Daxberger (University of Cambridge & MPI for Intelligent Systems, Tübingen) · Riccardo Barbano (University College London) · Eric Nalisnick (University of Amsterdam) · Jose Miguel Hernandez-Lobato (University of Cambridge)

Fast rates for noisy interpolation require rethinking the effect of inductive bias
Konstantin Donhauser (Swiss federal institute of technology) · Nicolò Ruggeri (ETH) · Stefan Stojanovic (ETH Zurich) · Fanny Yang (ETH Zurich)

Random Gegenbauer Features for Scalable Kernel Methods
Insu Han (Yale University) · Amir Zandieh ( MPI-INF) · Haim Avron (Tel Aviv University)

Accelerating Bayesian Optimization for Protein Design with Denoising Autoencoders
Samuel Stanton (New York University) · Wesley Maddox (New York University) · Nate Gruver (New York University) · Phillip Maffettone (BigHat Biosciences) · Emily Delaney (BigHat Biosciences) · Peyton Greenside (Bighat Biosciences) · Andrew Wilson (New York University)

Accelerated Federated Learning with Decoupled Adaptive Optimization
Jiayin Jin (Auburn University) · Jiaxiang Ren (Auburn University) · Yang Zhou (Auburn University) · Lingjuan Lyu (Sony AI Inc.) · Ji Liu (Baidu research) · Dejing Dou (Baidu)

A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks
Huan Zhang (CMU) · Shiqi Wang (Columbia) · Kaidi Xu (Northeastern University) · Yihan Wang (UCLA) · Suman Jana (Columbia University) · Cho-Jui Hsieh (UCLA) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI)

On the Convergence of Local Stochastic Compositional Gradient Descent with Momentum
Hongchang Gao (University of Pittsburgh) · Junyi Li (University of Pittsburgh) · Heng Huang (University of Pittsburgh & JD Finance America Corporation)

Hardness and Algorithms for Robust and Sparse Optimization
Eric Price (UT-Austin) · Sandeep Silwal (MIT) · Samson Zhou (School of Computer Science, Carnegie Mellon University)

Communication-Efficient Adaptive Federated Learning
Yujia Wang (Pennsylvania State University) · Lu Lin (University of Virginia) · Jinghui Chen (Penn State University)

An Exact Symbolic Reduction of Linear Smart Predict+Optimize to Mixed Integer Linear Programming
Jihwan Jeong (University of Toronto) · Parth Jaggi (University of Toronto) · Andrew Butler (University of Toronto) · Scott Sanner (University of Toronto)

ASAP-SGD: Instance-based Adaptiveness to Staleness in Asynchronous SGD
Karl Bäckström (Chalmers University of Technology) · Marina Papatriantafilou (Chalmers University of Technology) · Philippas Tsigas (Chalmers University of Technology)

Efficient Computation of Higher-Order Subgraph Attribution via Message Passing
Ping Xiong (Technical University Berlin) · Thomas Schnake (TU Berlin) · Grégoire Montavon (Technische Universität Berlin) · Klaus-robert Mueller (Technische Universität Berlin) · Shinichi Nakajima (TU Berlin)

HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning
Andrey Zhmoginov (Google Inc.) · Mark Sandler (Google) · Maksym Vladymyrov (Google)

Causal Dynamics Learning for Task-Independent State Abstraction
Zizhao Wang (University of Texas at Austin) · Xuesu Xiao (University of Texas at Austin) · Zifan Xu (University of Texas at Austin) · Yuke Zhu (University of Texas - Austin) · Peter Stone (The University of Texas at Austin and Sony AI)

EqR: Equivariant Representations for Data-Efficient Reinforcement Learning
Arnab Kumar Mondal (Mcgill University) · Vineet Jain (McGill University, Mila) · Kaleem Siddiqi (McGill University) · Siamak Ravanbakhsh (McGill - Mila)

Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion
Ling Yang (Peking University) · Shenda Hong (Peking University)

Marginal Distribution Adaptation for Discrete Sets via Module-Oriented Divergence Minimization
Hanjun Dai (Google Brain) · Mengjiao Yang (Google Brain) · Yuan Xue (Google) · Dale Schuurmans (Google / University of Alberta) · Bo Dai (Google Brain)

Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networkson Homogeneous Spaces
Yinshuang Xu (University of Pennsylvania) · Jiahui Lei (University of Pennsylvania) · Edgar Dobriban (University of Pennsylvania) · Kostas Daniilidis (University of Pennsylvania)

Semiparametric Subgraph Reasoning for Question Answering over Large Knowledge Bases
Rajarshi Das (University of Washington) · Ameya Godbole (USC) · Ankita Rajaram Naik (University of Massachusetts Amherst) · Elliot Tower (UMass Amherst) · Manzil Zaheer (Google Research) · Hannaneh Hajishirzi () · Robin Jia (USC) · Andrew McCallum (UMass Amherst)

Consistent Polyhedral Surrogates for Top-k Classification and Variants
Anish Thilagar (University of Colorado Boulder) · Rafael Frongillo (University of Colorado Boulder) · Jessie Finocchiaro (University of Colorado Boulder) · Emma Goodwill (University of Colorado Boulder)

Neural Inverse Transform Sampler
Henry Li (Yale University) · Yuval Kluger (Yale School of Medicine)

Extracting Latent State Representations with Linear Dynamics from Rich Observations
Abraham Frandsen (Duke University) · Rong Ge (Duke University) · Holden Lee (Duke University)

Provable Reinforcement Learning with a Short-Term Memory
Yonathan Efroni (Microsoft Research, New York) · Chi Jin (Princeton University) · Akshay Krishnamurthy (Microsoft Research) · Sobhan Miryoosefi (Princeton University)

A new similarity measure for covariate shift with applications to nonparametric regression
Reese Pathak (University of California, Berkeley) · Cong Ma (Princeton University) · Martin Wainwright (UC Berkeley / Voleon)

Correlated quantization for distributed mean estimation and optimization
Ananda Suresh (Google Research) · Ziteng Sun (Google Research) · Jae Ro (Google) · Felix Xinnan Yu (Google)

Steerable 3D Spherical Neurons
Pavlo Melnyk (Linköping University) · Michael Felsberg (Linköping University) · Mårten Wadenbäck (Linköping University)

Quantum-Inspired Algorithms from Randomized Numerical Linear Algebra
Nadiia Chepurko (MIT) · Kenneth Clarkson (IBM Research) · Lior Horesh (IBM Research) · Honghao Lin (Carnegie Mellon University) · David Woodruff (Carnegie Mellon University)

MAE-DET: Revisiting Maximal Entropy Principle in Zero-Shot NAS for Efficient Object Detection
Zhenhong Sun (Alibaba Group) · Ming Lin (Alibaba Group) · Zhiyu Tan (Alibaba Group) · Xiuyu Sun (Alibaba Group) · Hao Li (Alibaba Group) · rong jin (alibaba group)

Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training
Charbel Sakr (NVIDIA) · Steve Dai (NVIDIA) · Rangha Venkatesan (NVIDIA) · Brian Zimmer (NVIDIA) · William Dally (NVIDIA) · Brucek Khailany (NVIDIA)

Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration
Chengzhuo Ni (Princeton University) · Ruiqi Zhang (Peking University) · Xiang Ji (Princeton University) · Xuezhou Zhang (Princeton) · Mengdi Wang (Princeton University)

Content addressable memory without catastrophic forgetting by heteroassociation with a fixed scaffold
Sugandha Sharma (MIT) · Sarthak Chandra (Massachusetts Institute of Technology) · Ila R. Fiete (MIT)

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
Wenlong Huang (Google) · Pieter Abbeel (UC Berkeley & Covariant) · Deepak Pathak (Carnegie Mellon University) · Igor Mordatch (Google Brain)

Only tails matter: Average-Case Universality and Robustness in the Convex Regime
LEONARDO CUNHA (Universite de Montréal - MILA) · Gauthier Gidel (Mila) · Fabian Pedregosa (Google) · Courtney Paquette () · Damien Scieur (Samsung - SAIT AI Lab, Montreal)

Anytime Information Cascade Popularity Prediction via Self-Exciting Processes
Xi Zhang (Florida Institute of Technology) · Akshay Aravamudan (Florida Institute of Technology) · Georgios Anagnostopoulos (Florida Institute of Technology)

Transformer Quality in Linear Time
Weizhe Hua (Cornell University / Google Brain) · Zihang Dai () · Hanxiao Liu (Google Brain) · Quoc Le (Google Brain)

Towards Understanding Sharpness-Aware Minimization
Maksym Andriushchenko (EPFL) · Nicolas Flammarion (EPFL)

A deep convolutional neural network that is invariant to time rescaling
Brandon G Jacques (University of Virginia) · Zoran Tiganj (Indiana University) · Aakash Sarkar (Boston University) · Marc Howard (Boston University) · Per Sederberg (University of Virginia)

Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments
Ryan Sullivan (University of Maryland) · Jordan Terry (University of Maryland, College Park) · Benjamin Black (University of Maryland) · John P Dickerson (Arthur AI & Univ. of Maryland)

Online Balanced Experimental Design
David Arbour (Adobe Research) · Drew Dimmery (University of Vienna) · Tung Mai (Adobe Research) · Anup Rao (Adobe Research)

Global Optimization of K-Center Clustering
Mingfei Shi (University of British Columbia) · Kaixun Hua (University of British Columbia) · Jiayang Ren (The University of British Columbia) · Yankai Cao (University of British Columbia)

Controlling Conditional Language Models without Catastrophic Forgetting
Tomasz Korbak (University of Sussex) · Hady Elsahar (NaverLabs) · Germán Kruszewski (Naver Labs Europe) · Marc Dymetman (NAVER LABS Europe)

Private optimization in the interpolation regime: faster rates and hardness results
Hilal Asi (Stanford University) · Karan Chadha (Stanford University) · Gary Cheng (Stanford University) · John Duchi (Stanford University)

Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers
Arda Sahiner (Stanford University) · Tolga Ergen (Stanford University) · Batu M Ozturkler (Stanford University) · John Pauly (Stanford University) · Morteza Mardani (Stanford University) · Mert Pilanci (Stanford)

Minimax M-estimation under Adversarial Contamination
Sujay Bhatt (Baidu Research) · Guanhua Fang (Baidu USA) · Ping Li (Baidu Research) · Gennady Samorodnitsky (Cornell University)

Online Algorithms with Multiple Predictions
Keerti Anand (Duke University) · Rong Ge (Duke University) · Amit Kumar (IIT Delhi) · Debmalya Panigrahi (Duke University)

Counterfactual Transportability: A Formal Approach
Juan Correa (Universidad Autónoma de Manizales) · Sanghack Lee (Seoul National University) · Elias Bareinboim (Columbia)

Streaming Algorithms for High-Dimensional Robust Statistics
Ilias Diakonikolas (University of Wisconsin-Madison) · Daniel Kane (UCSD) · Ankit Pensia (University of Wisconsin-Madison) · Thanasis Pittas (University of Wisconsin-Madison)

Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks
Weiming Zhi (University of Sydney) · Tin Lai (The University of Sydney) · Lionel Ott (ETH) · Edwin V Bonilla (CSIRO's Data61) · Fabio Ramos (NVIDIA, University of Sydney)

Constrained Offline Policy Optimization
Nicholas Polosky (Andro Computational Solutions) · Bruno C. da Silva (University of Massachusetts) · Madalina Fiterau (University of Massachusetts Amherst) · Jithin Jagannath (ANDRO Computational Solutions)

Flow-based Recurrent Belief State Learning for POMDPs
Xiaoyu Chen (Tsinghua University) · Yao Mu (The University of Hong Kong) · Ping Luo (The University of Hong Kong) · Shengbo Li (Tsinghua University) · Jianyu Chen (Tsinghua University)

A Convergent and Dimension-Independent Min-Max Optimization Algorithm
Vijay Keswani (Yale University) · Oren Mangoubi (WPI) · Sushant Sachdeva (University of Toronto) · Nisheeth K. Vishnoi (Yale University)

Optimal Algorithms for Stochastic Multi-Level Compositional Optimization
Wei Jiang (Nanjing University) · Bokun Wang (The University of Iowa) · Yibo Wang (Nanjing University) · Lijun Zhang (Nanjing University) · Tianbao Yang (The University of Iowa)

Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
Amin Ghiasi (University of Maryland) · Hamid Kazemi (University of Maryland - College Park) · Steven Reich (University of Maryland) · Chen Zhu (UMD -> Google) · Micah Goldblum (New York University) · Tom Goldstein (University of Maryland)

Robust Fine-tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
Haotian Ju (Northeastern University) · Dongyue Li (Northeastern University) · Hongyang Zhang (Northeastern University)

The Role of Deconfounding in Meta-learning
Yinjie Jiang (Zhejiang University) · Zhengyu Chen (Zhejiang University) · Luotian Yuan (Zhejiang University) · Ying WEI (City University of Hong Kong) · Kun Kuang (Zhejiang University) · Xinhai Ye (Zhejiang University) · Zhihua Wang (Shanghai Institute for Advanced Study of Zhejiang University) · Fei Wu (Zhejiang University, China)

Data Determines Distributional Robustness in Contrastive Language Image Pre-training
Alex Fang (University of Washington) · Vaishaal Shankar (Amazon) · Achal Dave (Carnegie Mellon University) · Yuhao Wan (University of Washington, Seattle) · Gabriel Ilharco (University of Washington) · Mitchell Wortsman (University of Washington) · Ludwig Schmidt (Toyota Research Institute)

Lazy Estimation of Variable Importance for Large Neural Networks
Yue Gao (University of Wisconsin-Madison) · Abby Stevens (University of Chicago) · Garvesh Raskutti (UW-Madison) · Rebecca Willett (U Chicago)

Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
Yuxin Wen (University of Maryland) · Jonas Geiping (University of Maryland, College Park) · Liam Fowl (University of Maryland) · Micah Goldblum (New York University) · Tom Goldstein (University of Maryland)

H-Consistency Estimation Error of Surrogate Loss Minimizers
Pranjal Awasthi (Google) · Anqi Mao (Courant Institute of Mathematical Sciences, NYU) · Mehryar Mohri (Google Research and Courant Institute of Mathematical Sciences) · Yutao Zhong (Courant Institute of Mathematical Sciences, NYU)

Interpretable Off-Policy Learning via Hyperbox Search
Daniel Tschernutter (ETH Zurich) · Tobias Hatt (ETH Zurich) · Stefan Feuerriegel (LMU Munich)

Selective Network Linearization for Efficient Private Inference
Minsu Cho (NYU) · Ameya Joshi (New York University) · Brandon Reagen (New York University) · Siddharth Garg (New York University) · Chinmay Hegde (New York University)

It’s Raw! Audio Generation with State-Space Models
Karan Goel (Stanford) · Albert Gu (Stanford University) · Chris Donahue (Stanford) · Christopher Re (Stanford University)

Feature and Parameter Selection in Stochastic Linear Bandits
Ahmadreza Moradipari (University of California, Santa Barbara) · Berkay Turan (University of California, Santa Barbara) · Yasin Abbasi-Yadkori (DeepMind) · Mahnoosh Alizadeh (University of California Santa Barbara) · Mohammad Ghavamzadeh (Google Research)

Investigating Generalization by Controlling Normalized Margin
Alexander Farhang (Caltech) · Jeremy Bernstein (Caltech) · Kushal Tirumala (California Institute of Technology) · Yang Liu (Abacus.AI) · Yisong Yue (Caltech)

Retrieval-Augmented Reinforcement Learning
Anirudh Goyal (Université de Montréal) · Abe Friesen Friesen (DeepMind) · Andrea Banino (DeepMind) · Theophane Weber (DeepMind) · Nan Rosemary Ke (Google) · Adrià Puigdomenech Badia (Deepmind) · Arthur Guez (Google DeepMind) · Mehdi Mirza (DeepMind) · Peter Humphreys (Deepmind) · Ksenia Konyushkova (DeepMind) · Michal Valko (DeepMind / Inria / ENS Paris-Saclay) · Simon Osindero (DeepMind) · Timothy Lillicrap (Google DeepMind) · Nicolas Heess (DeepMind) · Charles Blundell (DeepMind)

Provably Adversarially Robust Nearest Prototype Classifiers
Václav Voráček (University of Tübingen) · Matthias Hein (University of Tübingen)

Accelerated, Optimal and Parallel: Some results on model-based stochastic optimization
Karan Chadha (Stanford University) · Gary Cheng (Stanford University) · John Duchi (Stanford University)

The Unsurprising Effectiveness of Pre-Trained Vision Models for Control
Simone Parisi (Meta AI) · Aravind Rajeswaran (FAIR) · Senthil Purushwalkam (Carnegie Mellon University) · Abhinav Gupta (Facebook)

Zero-Shot Reward Specification via Grounded Natural Language
Parsa Mahmoudieh (UC Berkeley) · Deepak Pathak (Carnegie Mellon University) · Trevor Darrell (University of California at Berkeley)

PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information
Changbin Li (The University of Texas at Dallas) · Suraj Kothawade (University of Texas at Dallas) · Feng Chen (UT Dallas) · Rishabh Iyer (University of Texas at Dallas)

Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
Mayee Chen (Stanford University) · Dan Fu (Stanford University) · Avanika Narayan (Stanford University) · Michael Zhang (Stanford University) · Zhao Song (Adobe Research) · Kayvon Fatahalian (Stanford) · Christopher Re (Stanford University)

Linear Complexity Randomized Self-attention Mechanism
Lin Zheng (The University of Hong Kong) · Chong Wang (ByteDance) · Lingpeng Kong (The University of Hong Kong)

GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing
Zhongkai Hao (Tsinghua University) · Chengyang Ying (Tsinghua University) · Yinpeng Dong (Tsinghua University) · Hang Su (Tsinghua University) · Jian Song (Tsinghua University) · Jun Zhu (Tsinghua University)

Variational Mixtures of ODEs for Inferring Cellular Gene Expression Dynamics
Yichen Gu (University of Michigan) · Joshua Welch (University of Michigan) · DAVID BLAAUW (University of Michigan)

Measure Estimation in the Barycentric Coding Model
Matthew Werenski (Tufts University) · Ruijie Jiang (Tufts University) · Abiy Tasissa (Tufts University) · Shuchin Aeron (Tufts University) · James Murphy (Tufts University)

Difference Advantage Estimation for Multi-Agent Policy Gradients
yueheng li (Peking university) · Guangming Xie (1. State Key Laboratory for Turbulence and Complex Systems, College of Engineering, Peking University; 2. Center for Multi-Agent Research, Institute for Artificial Intelligence, Peking University) · Zongqing Lu (Peking University)

Online Continual Learning through Mutual Information Maximization
Yiduo Guo (Peking University) · Bing Liu (University of Illinois at Chicago) · Dongyan Zhao (Peking Univeristy)

HyperPrompt: Prompt-based Task-Conditioning of Transformers
Steven Zheng (Google) · Yun He (Meta (Facebook) AI) · Yu Du (Google Research) · Don Metzler (Google) · Ed Chi (Google) · Heng-Tze Cheng (Google Research) · Jai Gupta (Google) · Vamsi Aribandi (Google) · Yaguang Li (Google) · Yi Tay (Google) · Zhao Chen (Google) · Zhe Zhao (Google AI)

Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning
Shentao Yang (University of Texas at Austin) · Yihao Feng (The University of Texas at Austin) · Shujian Zhang (UT Austin) · Mingyuan Zhou (University of Texas at Austin)

Adversarially trained neural representations are already as robust as biological neural representations
Chong Guo (Massachusetts Institute of Technology) · Michael Lee (MIT) · Guillaume Leclerc (MIT) · Joel Dapello (Harvard University) · Yug Rao (Purdue University) · Aleksander Madry (MIT) · James DiCarlo (Massachusetts Institute of Technology)

Modular Conformal Calibration
Shengjia Zhao (Stanford University) · Charles Marx (Stanford University) · Willie Neiswanger (Stanford University) · Stefano Ermon (Stanford University)

Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale
Samyam Rajbhandari (Microsoft) · Conglong Li (Microsoft) · Zhewei Yao (University of California, Berkeley) · Minjia Zhang (Microsoft) · Reza Yazdani Aminabadi (microsoft) · Ammar Ahmad Awan (Microsoft) · Jeff Rasley (Microsoft) · Yuxiong He (Microsoft)

Nonparametric Involutive Markov Chain Monte Carlo
Carol Mak (University of Oxford) · Fabian Zaiser (University of Oxford) · Luke Ong (University of Oxford)

Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)
Huang Bojun (Rakuten Institute of Technology)

Generative Modeling for Multitask Visual Learning
Zhipeng Bao (Carnegie Mellon University) · Yu-Xiong Wang (University of Illinois at Urbana-Champaign) · Martial Hebert (Carnegie Mellon School of Computer Science)

Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent
Pedro Soto (The Graduate Center, CUNY) · Ilia Ilmer (CUNY Graduate Center) · Haibin Guan (Icahn School of Medicine at Mount Sinai) · Jun Li (City University of New York)

Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling
Hongkang Li (Rensselaer Polytechnic Institute) · Meng Wang (Rensselaer Polytechnic Institute) · Sijia Liu (Michigan State University) · Pin-Yu Chen (IBM Research AI) · Jinjun Xiong (University at Buffalo)

A Simple yet Universal Strategy for Online Convex Optimization
Lijun Zhang (Nanjing University) · Guanghui Wang (Georgia Tech) · Jinfeng Yi (JD AI Research) · Tianbao Yang (The University of Iowa)

Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits
Qinghua Liu (Princeton University) · Yuanhao Wang (Princeton University) · Chi Jin (Princeton University)

LCANets: Lateral Competition Improves Robustness Against Corruption and Attack
Michael Teti (Los Alamos National Laboratory) · Juston Moore (Los Alamos National Laboratory) · Garrett T Kenyon (Los Alamos National Laboratory) · Benjamin Migliori (Los Alamos National Lab)

Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time
Burak Bartan (Stanford University) · Mert Pilanci (Stanford)

Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood
Qiujiang Jin (University of Texas at Austin) · Alec Koppel (JP Morgan Chase AI Research) · Ketan Rajawat (Indian Institute of Technology Kanpur) · Aryan Mokhtari (UT Austin)

Partial Counterfactual Identification from Observational and Experimental Data
Junzhe Zhang (Columbia University) · Jin Tian (Iowa State University) · Elias Bareinboim (Columbia)

3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design
Yinan Huang (Beijing Institute for General Artifitial Intelligence) · Xingang Peng (Tsinghua University) · Jianzhu Ma (Institute for Artificial Intelligence, Peking University) · Muhan Zhang (Peking University)

Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets
Xingang Peng (Tsinghua University) · Shitong Luo (Peking University) · Jiaqi Guan (UIUC) · Qi Xie (Westlake University) · Jian Peng (UIUC) · Jianzhu Ma (Institute for Artificial Intelligence, Peking University)

Asymptotically-Optimal Gaussian Bandits with Side Observations
Alexia Atsidakou (University of Texas at Austin) · Orestis Papadigenopoulos (The University of Texas at Austin) · Constantine Caramanis (University of Texas) · Sujay Sanghavi (UT Austin) · Sanjay Shakkottai (University of Texas at Austin)

On Last-Iterate Convergence Beyond Zero-Sum Games
Ioannis Anagnostides (Carnegie Mellon University) · Ioannis Panageas (UC Irvine) · Gabriele Farina (Carnegie Mellon University) · Tuomas Sandholm (Carnegie Mellon University)

Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
Katie Kang (UC Berkeley) · Paula Gradu (UC Berkeley) · Michael Janner (UC Berkeley) · Jason Choi (UC Berkeley) · Claire Tomlin (UC Berkeley) · Sergey Levine (University of California, Berkeley)

Privacy for Free: How does Dataset Condensation Help Privacy?
Tian Dong (Shanghai Jiao Tong University) · Bo Zhao (The University of Edinburgh) · Lingjuan Lyu (Sony AI)

Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity
Lin Guan (Arizona State University) · Sarath Sreedharan (ASU) · Subbarao Kambhampati (Arizona State University)

Transformers are Meta-Reinforcement Learners
Luckeciano Melo (Microsoft)

A Statistical Manifold Framework for Point Cloud Data
Yonghyeon Lee (Seoul National University) · Seungyeon Kim (Seoul National University) · Jinwon Choi (kakaoenterprise) · Frank Chongwoo Park (Seoul National University)

Universal and data-adaptive algorithms for model selection in linear contextual bandits
Vidya Muthukumar (Georgia Institute of Technology) · Akshay Krishnamurthy (Microsoft Research)

Not All Poisons are Created Equal: Robust Training against Data Poisoning
Yu Yang (University of California, Los Angeles) · Tian Yu Liu (UCLA) · Baharan Mirzasoleiman (Stanford University)

Fast Lossless Neural Compression with Integer-Only Discrete Flows
Siyu Wang (Tsinghua University) · Jianfei Chen (Tsinghua University) · Chongxuan Li (Tsinghua University) · Jun Zhu (Tsinghua University) · Bo Zhang (Tsinghua University)

Multi-scale Feature Learning Dynamics: Insights for Double Descent
Mohammad Pezeshki (Mila, Université de Montréal) · Amartya Mitra (Capgemini America Inc.) · Yoshua Bengio (Mila - Quebec AI Institute) · Guillaume Lajoie (Mila, Université de Montréal)

On Implicit Bias in Overparameterized Bilevel Optimization
Paul Vicol (University of Toronto) · Jonathan Lorraine (University of Toronto) · Fabian Pedregosa (Google) · David Duvenaud (University of Toronto) · Roger Grosse (University of Toronto and Vector Institute)

One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence Streams
Benjamin Coleman (Rice University) · Benito Geordie (S01290073) · Li Chou (Rice University) · R. A. Leo Elworth (Rice University) · Todd Treangen (Rice University) · Anshumali Shrivastava (Rice University)

Supervised Off-Policy Ranking
Yue Jin (Tsinghua University) · Yue Zhang (University of Science and Technology of China) · Tao Qin (Microsoft Research Asia) · Xudong Zhang (Tsinghua university) · Jian Yuan (Tsinghua University) · Houqiang Li (University of Science and Technology of China) · Tie-Yan Liu (Microsoft Research Asia)

Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
Aaron Mishkin (Stanford University) · Mert Pilanci (Stanford) · Arda Sahiner (Stanford University)

AutoIP: A United Framework to Integrate Physics into Gaussian Processes
Da Long (The University of Utah) · Zheng Wang (University of Utah) · Aditi Krishnapriyan (UC Berkeley) · Robert Kirby (University of Utah) · Shandian Zhe (University of Utah) · Michael Mahoney (UC Berkeley)

Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
Shuang Qiu (University of Chicago) · Lingxiao Wang (Northwestern University) · Chenjia Bai (Harbin Institute of Technology) · Zhuoran Yang (Yale University) · Zhaoran Wang (Northwestern University)

Improved StyleGAN-v2 based Inversion for Out-of-Distribution Images
Rakshith Subramanyam (Arizona State University) · Vivek Narayanaswamy (Arizona State University) · Mark Naufel (Arizona State University) · Andreas Spanias (ASU) · Jayaraman J. Thiagarajan (Lawrence Livermore National Laboratory)

Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization
Brandon Trabucco (Carnegie Mellon University) · Xinyang Geng (UC Berkeley) · Aviral Kumar (UC Berkeley) · Sergey Levine (UC Berkeley)

Information Bottleneck-Guided Stochastic Attention Mechanism for Interpretable Graph Learning
Siqi Miao (Purdue University) · Pan Li (Purdue University) · Mia Liu (Purdue University)

Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence Analysis
Jungbin Kim (Seoul National University) · Insoon Yang (Seoul National University)

Certified Adversarial Robustness Under the Bounded Support Set
Yiwen Kou (Peking University) · Qinyuan Zheng (Peking University) · Yisen Wang (Peking University)

Learning Transferable Polices By Inferring Agent Morphology
Brandon Trabucco (Carnegie Mellon University) · mariano phielipp (Intel AI Labs) · Glen Berseth (Universite de Montreal/Mila)

Wide Neural Networks Forget Less Catastrophically
Seyed Iman Mirzadeh (Washington State University) · Arslan Chaudhry (DeepMind) · Dong Yin (DeepMind) · Huiyi Hu (DeepMind) · Razvan Pascanu (DeepMind) · Dilan Gorur () · Mehrdad Farajtabar (Google DeepMind)

Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging
Shishir G. Patil (UC Berkeley) · Paras Jain (UC Berkeley) · Prabal Dutta (UC Berkeley) · Ion Stoica (UC Berkeley) · Joseph E Gonzalez (UC Berkeley)

Stochastic Reweighted Gradient Descent
Ayoub El Hanchi (University of Toronto) · David Stephens (McGill University) · Chris Maddison (University of Toronto)

Learning Bellman Complete Representations for Offline Policy Evaluation
Jonathan Chang (Cornell University) · Kaiwen Wang (Cornell University and Cornell Tech) · Nathan Kallus (Cornell University) · Wen Sun (Cornell University)

Offline Meta-Reinforcement Learning with Online Self-Supervision
Vitchyr Pong (UC Berkeley, OpenAI) · Ashvin Nair (UC Berkeley) · Laura Smith (UC Berkeley) · Catherine Huang (UC Berkeley) · Sergey Levine (UC Berkeley)

Learning to Assemble with Large-Scale Structured Reinforcement Learning
Seyed Kamyar Seyed Ghasemipour (University of Toronto) · Satoshi Kataoka (Google LLC) · Byron David (Google) · Daniel Freeman (Google Brain) · Shixiang Gu (Google) · Igor Mordatch (Google Brain)

Adaptive Second Order Coresets for Data-efficient Machine Learning
Omead Pooladzandi (University of California, Los Angeles) · David Davini (UCLA) · Baharan Mirzasoleiman (Stanford University)

MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer
JEON JEEWON (Korea Advanced Institute of Science and Technology) · WOOJUN KIM (KAIST) · Whiyoung Jung (KAIST) · Youngchul Sung (KAIST)

Symmetric Machine Theory of Mind
Melanie Sclar (University of Washington) · Graham Neubig (Carnegie Mellon University) · Yonatan Bisk (Carnegie Mellon University)

Fused Acoustic and Text Pretraining for Speech Synthesis and Editing
He Bai (University of Waterloo) · Renjie Zheng (Baidu Research) · Junkun Chen (Oregon State University) · Mingbo Ma (Baidu Research) · Xintong Li (Baidu Research) · Liang Huang (Baidu Research USA and Oregon State University)

Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning
Adam Villaflor (Carnegie Mellon University) · Zhe Huang (Carnegie Mellon University) · Swapnil Pande (Carnegie Mellon University) · John Dolan (Carnegie Mellon University) · Jeff Schneider (CMU/Uber)

De novo mass spectrometry peptide sequencing with a transformer model
Melih Yilmaz (University of Washington) · William Fondrie (Talus Bioscience) · Wout Bittremieux (University of California San Diego) · Sewoong Oh (University of Washington) · William Noble (University of Washington)

Divergence-Regularized Multi-Agent Actor-Critic
Kefan Su (peking university) · Zongqing Lu (Peking University)

Learning to Separate Voices by Spatial Regions
Zhongweiyang Xu (University of Illinois Urbana Champaign) · Romit Roy Choudhury (University of Illinois Urbana-Champaign)

Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models.
Abhineet Agarwal (University of California, Berkeley) · Yan Shuo Tan (Berkeley) · omer ronen (uc berkeley) · Chandan Singh (UC Berkeley) · Bin Yu (University of California, Berkeley)

Off-Policy Reinforcement Learning with Delayed Rewards
Beining Han (Tsinghua University) · Zhizhou Ren (University of Illinois at Urbana-Champaign) · Zuofan Wu (Helixon Research) · Yuan Zhou (UIUC) · Jian Peng (UIUC)

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning
Philippe Hansen-Estruch (University of California, Berkeley) · Amy Zhang (FAIR / UC Berkeley) · Ashvin Nair () · Patrick Yin (UC Berkeley) · Sergey Levine (University of California, Berkeley)

DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations
Fei Deng (Rutgers University) · Ingook Jang (ETRI) · Sungjin Ahn (KAIST)

DAVINZ: Data Valuation using Deep Neural Networks at Initialization
Zhaoxuan Wu (National University of Singapore) · Yao Shu (National University of Singapore) · Bryan Kian Hsiang Low (National University of Singapore)

Langevin Monte Carlo for Contextual Bandits
Pan Xu (California Institute of Technology) · Hongkai Zheng (Caltech) · Eric Mazumdar (Caltech) · Kamyar Azizzadenesheli (Purdue University) · Animashree Anandkumar (Caltech and NVIDIA)

Online Active Regression
Cheng Chen (Nanyang Technological University) · Yi Li (Nanyang Technological University) · Yiming Sun (Nanyang Technological University)

Adaptive Model Design for Markov Decision Process
Siyu Chen (Tsinghua University) · Donglin Yang (Tsinghua University) · Jiayang Li (Northwestern University) · Senmiao Wang (Northwestern University) · Zhuoran Yang (Yale University) · Zhaoran Wang (Northwestern University)

Reachability Constrained Reinforcement Learning
Dongjie Yu (Tsinghua University) · Haitong Ma (Tsinghua University) · Shengbo Li (Tsinghua University) · Jianyu Chen (Tsinghua University)

Faster Privacy Accounting via Evolving Discretization
Badih Ghazi (Google) · Pritish Kamath (Google Research) · Ravi Kumar (Google) · Pasin Manurangsi (Google Research)

The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation
Wei-Ning Chen (Stanford University) · Ayfer Ozgur (Stanford University) · Peter Kairouz (Google)

Directed Acyclic Transformer for Non-Autoregressive Machine Translation
Fei Huang (Tsinghua University) · Hao Zhou (Bytedance) · Yang Liu (Tsinghua University) · Hang Li (Bytedance Technology) · Minlie Huang (Tsinghua University)

Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?
Keshigeyan Chandrasegaran (Singapore University of Technology and Design (SUTD)) · Ngoc-Trung Tran (Singapore University of Technology and Design) · Yunqing Zhao (Singapore University of Technology and Design) · Ngai-Man Cheung (Singapore University of Technology and Design)

Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging
Anastasios Angelopoulos (UC Berkeley) · Amit Pal Kohli (University of California, Berkeley) · Stephen Bates (University of California, Berkeley) · Michael Jordan (UC Berkeley) · Jitendra Malik (University of California at Berkeley) · Thayer Alshaabi (University of California, Berkeley) · Srigokul Upadhyayula (University of California, Berkeley) · Yaniv Romano (Technion---Israel Institute of Technology)

Parametric Visual Program Induction with Function Modularization
Xuguang Duan (Tsinghua University) · Xin Wang (Tsinghua University) · Ziwei Zhang (Tsinghua University) · Wenwu Zhu (Tsinghua University)

Dynamic Regret of Online Markov Decision Processes
Long-Fei Li (Nanjing University) · Peng Zhao (Nanjing University) · Zhi-Hua Zhou (Nanjing University)

Action-Sufficient State Representation Learning for Control with Structural Constraints
Biwei Huang (Carnegie Mellon University) · Chaochao Lu (University of Cambridge) · Liu Leqi (Carnegie Mellon University) · Jose Miguel Hernandez-Lobato (University of Cambridge) · Clark Glymour (Carnegie Mellon University) · Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany) · Kun Zhang (Carnegie Mellon University)

Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
Kyunghwan Son (KAIST) · Junsu Kim (KAIST) · Sungsoo Ahn (None) · Roben Delos Reyes (Korea Advanced Institute of Science and Technology) · Yung Yi (KAIST) · Jinwoo Shin (KAIST)

Convergence Results for Predictive Coding Networks
Simon Frieder (University of Oxford) · Thomas Lukasiewicz (TU Wien and University of Oxford)

Diffusion bridges vector quantized variational autoencoders
Max Cohen (Télécom SudParis, Oze Energies) · Guillaume QUISPE (Polytechnique) · Sylvain Le Corff (Télécom SudParis) · Charles Ollion (Polytechnique, IPP) · Eric Moulines (Ecole Polytechnique)

Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning
Yang Zhao (Tsinghua University) · Hao Zhang (Tsinghua University) · Xiuyuan Hu (Tsinghua University)

ActiveHedge: Hedge meets Active Learning
Bhuvesh Kumar (Georgia Institute of Technology) · Jacob Abernethy (Georgia Institute of Technology) · Venkatesh Saligrama (Boston University)

Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning
Martin Genzel (Helmholtz-Zentrum Berlin) · Ingo Gühring (Technische Universität Berlin) · Jan Macdonald (Technische Universität Berlin) · Maximilian März (TU Berlin)

Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets
Hongxin Wei (Nanyang Technological University) · Lue Tao (Nanjing University of Aeronautics and Astronautics) · RENCHUNZI XIE (Nanyang Technological University) · LEI FENG (Nanyang Technological University) · Bo An (Nanyang Technological University)

Matching Learned Causal Effects of Neural Networks with Domain Priors
Gowtham Reddy Abbavaram (Indian Institute of Technology Hyderabad) · Sai Srinivas Kancheti (Indian Institute of Technology Hyderabad) · Vineeth N Balasubramanian (Indian Institute of Technology, Hyderabad) · Amit Sharma (Microsoft Research)

Improving Ensemble Distillation with Weight Averaging and Diversifying Perturbation
Giung Nam (KAIST) · Hyungi Lee (KAIST) · Byeongho Heo (NAVER AI LAB) · Juho Lee (KAIST, AITRICS)

On the Learning of Non-autoregressive Transformers
Fei Huang (Tsinghua University) · Tianhua Tao (Tsinghua University) · Hao Zhou (Bytedance) · Lei Li (University of California Santa Barbara) · Minlie Huang (Tsinghua University)

Cross-Space Active Learning on Graph Convolutional Networks
Yufei Tao (The Chinese University of Hong Kong) · Hao WU (The Chinese University of Hong Kong) · Shiyuan Deng (the Chinese University of Hong Kong)

TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification
Jaeyun Song (KAIST) · Joonhyung Park (KAIST) · Eunho Yang (KAIST,AITRICS)

A multi-objective / multi-task learning framework induced by Pareto stationarity
Michinari Momma (Amazon) · Chaosheng Dong (Amazon) · Jia Liu (The Ohio State University)

Temporal Difference Learning for Model Predictive Control
Nicklas Hansen (University of California, San Diego) · Hao Su (UCSD) · Xiaolong Wang (UCSD)

ProxSkip: A Simple and Provably Effective Communication-Acceleration Technique for Federated Learning
Konstantin Mishchenko (CNRS) · Grigory Malinovsky (KAUST) · Sebastian Stich (CISPA Helmholtz Center for Information Security gGmbH) · Peter Richtarik (KAUST)

Improving Policy Optimization with Generalist-Specialist Learning
Zhiwei Jia (University of California, San Diego) · Xuanlin Li (UCSD) · Zhan Ling (UCSD) · Shuang Liu (University of California, San Diego) · Yiran Wu (University of California, San Diego) · Hao Su (UCSD)

Sparsity in Partially Controllable Linear Systems
Yonathan Efroni (Microsoft Research, New York) · Sham Kakade (Harvard University) · Akshay Krishnamurthy (Microsoft Research) · Cyril Zhang (Microsoft Research)

Counterfactual Prediction for Outcome-oriented Treatments
Hao Zou (Tsinghua University) · Peng Cui (Tsinghua University) · Bo Li (Tsinghua University) · Jiangang Han (Meituan) · Shuiping Chen (Meituan) · Xuetao Ding (meituan)

Gradient Descent on Neurons and its Link to Approximate Second-order Optimization
Frederik Benzing (ETH Zurich)

3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation
Peter Richtarik (KAUST) · Igor Sokolov (King Abdullah University of Science and Technology) · Elnur Gasanov (KAUST) · Ilyas Fatkhullin (ETH Zurich) · Zhize Li (KAUST and CMU) · Eduard Gorbunov (Moscow Institute of Physics and Technology)

VarScene: A Deep Generative Model for Realistic Scene Graph Synthesis
Tathagat Verma (IIT Bombay) · Abir De (IIT Bombay) · Yateesh Agrawal (IIT Bombay) · Vishwa Vinay (Adobe Research) · Soumen Chakrabarti (IIT Bombay)

Boosting Graph Structure Learning with Dummy Nodes
Xin Liu (Hong Kong University of Science and Technology) · Jiayang Cheng (The Hong Kong University of Science and Technology) · Yangqiu Song (Hong Kong University of Science and Technology) · Xin Jiang (Huawei Noah's Ark lab)

Individual Reward Assisted Multi-Agent Reinforcement Learning
Li Wang (Nanjing University) · Yujing Hu (NetEase Fuxi AI Lab) · Yupeng Zhang (Nanjing University) · Weixun Wang (Tianjin University) · Chongjie Zhang (Tsinghua University) · Yang Gao (Nanjing University) · Jianye Hao (Tianjin University) · Tangjie Lv (NetEase Fuxi AI Lab) · Changjie Fan (NetEase Fuxi AI Lab)

Neural language models are not born equal to fit brain data, but training helps
Alexandre Pasquiou (INRIA, NEUROSPIN) · Yair Lakretz (NeuroSPin, Paris) · Christophe Pallier (INSERM/CEA/UNICOG) · Thirion Bertrand (inria) · John Hale (University of Georgia)

Implicit Regularization with Polynomial Growth in Deep Tensor Factorization
Kais HARIZ (AMU) · Hachem Kadri (Aix-Marseille University) · Stephane Ayache (AMU LIS) · Maher Moakher (Ecole Nationale d'Ingénieurs de Tunis) · Thierry Artieres ()

AdaGrad Avoids Saddle Points
Kimon Antonakopoulos (EPFL) · Panayotis Mertikopoulos (CNRS and Criteo AI Lab) · Georgios Piliouras (Singapore University of Technology and Design) · Xiao Wang (Shanghai University of Finance and Economics)

Bayesian Optimization for Distributionally Robust Chance-constrained Problem
Yu Inatsu (Nagoya Institute of Technology) · Shion Takeno (Nagoya Institute of Technology) · Masayuki Karasuyama (Nagoya Institute of Technology) · Ichiro Takeuchi (Nagoya Institute of Technology / RIKEN)

Fair and Fast k-Center Clustering for Data Summarization
Haris Angelidakis (CoW Protocol) · Adam Kurpisz (ETH Zurich) · Leon Sering (ETH Zurich) · Rico Zenklusen (ETH Zurich)

Multicoated Supermasks Enhance Hidden Networks
Yasuyuki Okoshi (Tokyo Institute of Technology) · Ángel López García-Arias (Tokyo Institute of Technology) · Kazutoshi Hirose (Tokyo Institute of Technology) · Kota Ando (Tokyo Institute of Technology) · Kazushi Kawamura (Tokyo Institute of Technology) · Thiem Van Chu (Tokyo Institute of Technology) · Masato Motomura (Tokyo Institute of Technology) · Jaehoon Yu (Tokyo Institute of Technology)

Nonlinear Feature Diffusion on Hypergraphs
Konstantin Prokopchik (Gran Sasso Science Institute) · Austin Benson (Cornell University) · Francesco Tudisco (Gran Sasso Science Institute)

Towards Coherent and Consistent Use of Entities in Narrative Generation
Pinelopi Papalampidi (University of Edinburgh) · Kris Cao (DeepMind) · Tomas Kocisky (DeepMind)

Representation Topology Divergence: A Method for Comparing Neural Network Representations.
Serguei Barannikov (Skolkovo Institute of Science and Technology) · Ilya Trofimov (Skoltech) · Nikita Balabin (Skolkovo Institute of Science and Technology) · Evgeny Burnaev (Skoltech)

On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs
Yuanzhou Chen (Peking University) · Jiafan He (University of California, Los Angeles) · Quanquan Gu (University of California, Los Angeles)

LIDL: Local Intrinsic Dimension estimation using approximate Likelihood
Piotr Tempczyk (University of Warsaw) · Rafał Michaluk (University of Warsaw) · Łukasz Garncarek (Applica.ai) · Adam Golinski (University of Oxford) · Przemysław Spurek (Jagiellonian University) · Jacek Tabor (Jagiellonian University in Kraków)

Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation
Volodymyr Kuleshov (Cornell University) · Shachi Deshpande (Cornell University)

On the Convergence of the Shapley Value in Parametric Bayesian Learning Games
Lucas Agussurja (National University of Singapore) · Xinyi Xu (National University of Singapore) · Bryan Kian Hsiang Low (National University of Singapore)

Convergence of policy gradient for entropy regularized MDPs with neural network approximation in the mean-field regime
James-Michael Leahy (Imperial College London) · Bekzhan Kerimkulov (University of Edinburgh) · David Siska (University of Edinburgh) · Lukasz Szpruch (University of Edinburgh/The Alan Turing Institute)

Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
Bodhisattwa Prasad Majumder (UC San Diego) · Oana-Maria Camburu (University of Oxford) · Thomas Lukasiewicz (TU Wien and University of Oxford) · Julian McAuley (UCSD)

Quantifying and Learning Linear Symmetry-Based Disentanglement
Loek Tonnaer (Eindhoven University of Technology) · Luis Armando Perez Rey (Eindhoven University of Technology) · Vlado Menkovski (Eindhoven University of Technology) · Mike Holenderski (Eindhoven University of Technology) · Jacobus Portegies (Eindhoven University of Technology)

Time Is MattEr: Temporal Self-supervision for Video Transformers
Sukmin Yun (KAIST) · Jaehyung Kim (KAIST) · Dongyoon Han (NAVER AI Lab) · Hwanjun Song (NAVER AI Lab) · Jung-Woo Ha (Clova AI Research, NAVER Corp.) · Jinwoo Shin (KAIST)

Mitigating modality collapse in multimodal VAEs via impartial optimization
Adrián Javaloy (Saarland University) · Maryam Meghdadi (Saarland University) · Isabel Valera (Saarland University)

On the Surrogate Gap between Contrastive and Supervised Losses
Han Bao (The University of Tokyo / RIKEN) · Yoshihiro Nagano (The University of Tokyo/RIKEN) · Kento Nozawa (The University of Tokyo and RIKEN)

SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization
Yuhta Takida (Sony Group Corporation) · Takashi Shibuya (Sony Group Corporation) · WeiHsiang Liao (Sony Group Corporation) · Chieh-Hsin Lai (Sony Group Corporation) · Junki Ohmura (Sony Group Corporation) · Toshimitsu Uesaka (Sony Group Corporation) · Naoki Murata (Sony Group Corporation) · Shusuke Takahashi (Sony Group Corporation) · Toshiyuki Kumakura (Sony Corporation of America) · Yuki Mitsufuji (Sony Group Corporation)

Attentional meta-learners for few-shot polythetic classification
Ben Day (University of Cambridge) · Ramon Viñas Torné (University of Cambridge) · Nikola Simidjievski (University of Cambridge) · Pietro Lió (University of Cambridge)

Heteroscedastic Noise Based Causal Inference
Sascha Xu (Saarland University) · Osman Ali Mian (CISPA Helmholtz Center for Information Security) · Alexander Marx (ETH Zürich) · Jilles Vreeken (CISPA Helmholtz Center for Information Security)

Bregman Neural Networks
Jordan Frecon (INSA Rouen) · Saverio Salzo (Istituto Italiano di Tecnologia) · Massimiliano Pontil ( Istituto Italiano di Tecnologia & University College London) · Gilles Gasso (INSA Rouen)

A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications
Lukas Wolf (ETH Zürich) · Ard Kastrati (ETH Zurich) · Martyna Plomecka (University of Zurich) · Alexander Veicht (ETH Zürich) · Dustin Klebe (ETH Zurich) · Jieming Li (ETH Zürich) · Roger Wattenhofer (ETH Zurich) · Nicolas Langer (University of Zurich)

Differential Privacy Has Disparate Impact on Generative Models and Synthetic Data
Georgi Ganev (UCL & Hazy) · (None) · Emiliano De Cristofaro (University College London)

Batch Greenkhorn Algorithm for Entropic-Regularized Multimarginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity
Vladimir Kostic (Istituto Italiano di Tecnologia) · Saverio Salzo (Istituto Italiano di Tecnologia) · Massimiliano Pontil ( Istituto Italiano di Tecnologia & University College London)

Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology
Yan Huang (Zhejiang University) · Ying Sun (The Pennsylvania State University) · Zehan Zhu (Zhejiang University) · Changzhi Yan (Zhejiang University) · Jinming Xu (Zhejiang University)

Equivariant Priors for compressed sensing with unknown orientation
Anna Kuzina (Vrije Universiteit Amsterdam) · Kumar Pratik (Qualcomm AI Research, NL) · Fabio Valerio Massoli (Qualcomm AI) · Arash Behboodi (Qualcomm AI Research)

Scalable Deep Reinforcement Learning Algorithms for Mean Field Games
Mathieu Lauriere (Google Brain) · Sarah Perrin (Univ. Lille) · Sertan Girgin (Google Brain) · Paul Muller (Deepmind) · Ayush Jain (University of California, Berkeley) · Theophile Cabannes (Google) · Georgios Piliouras (SUTD) · Julien Perolat (DeepMind) · Romuald Elie (Deepmind) · Olivier Pietquin (GOOGLE BRAIN) · Matthieu Geist (Google)

Neural Network Poisson Models for Behavioural and Neural Spike Train Data
Moein Khajehnejad (Monash University) · Forough Habibollahi (University of Melbourne) · Richard Nock (Google Research) · Ehsan Arabzadeh (ANU) · Peter Dayan (MPI for Biological Cybernetics) · Amir Dezfouli (CSIRO's Data61)

Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness
Kevin Scaman (INRIA Paris) · Cedric Malherbe (Huawei Noah's Ark Lab) · Ludovic DOS SANTOS (Huawei Technologies France S.A.S.U)

On Distribution Shift in Learning-based Bug Detectors
Jingxuan He (ETH Zurich) · Luca Beurer-Kellner (ETH Zürich) · Martin Vechev (ETH Zurich)